Identifying phone inventories is a crucial component in language documentation and the preservation of endangered languages. However, even the largest collection of phone inventory only covers about 2000 languages, which is only 1/4 of the total number of languages in the world. A majority of the remaining languages are endangered. In this work, we attempt to solve this problem by estimating the phone inventory for any language listed in Glottolog, which contains phylogenetic information regarding 8000 languages. In particular, we propose one probabilistic model and one non-probabilistic model, both using phylogenetic trees (“language family trees”) to measure the distance between languages. We show that our best model outperforms baseline models by 6.5 F1. Furthermore, we demonstrate that, with the proposed inventories, the phone recognition model can be customized for every language in the set, which improved the PER (phone error rate) in phone recognition by 25%.

Films are a rich source of data for natural language processing. OpenSubtitles (Lison and Tiedemann, 2016) is a popular movie script dataset, used for training models for tasks such as machine translation and dialogue generation. However, movies often contain biases that reflect society at the time, and these biases may be introduced during pre-training and influence downstream models. We perform sentiment analysis on template infilling (Kurita et al., 2019) and the Sentence Embedding Association Test (May et al., 2019) to measure how BERT-based language models change after continued pre-training on OpenSubtitles. We consider gender bias as a primary motivating case for this analysis, while also measuring other social biases such as disability. We show that sentiment analysis on template infilling is not an effective measure of bias due to the rarity of disability and gender identifying tokens in the movie dialogue. We extend our analysis to a longitudinal study of bias in film dialogue over the last 110 years and find that continued pre-training on OpenSubtitles encodes additional bias into BERT. We show that BERT learns associations that reflect the biases and representation of each film era, suggesting that additional care must be taken when using historical data.

Grapheme-to-Phoneme (G2P) has many applications in NLP and speech fields. Most existing work focuses heavily on languages with abundant training datasets, which limits the scope of target languages to less than 100 languages. This work attempts to apply zero-shot learning to approximate G2P models for all low-resource and endangered languages in Glottolog (about 8k languages). For any unseen target language, we first build the phylogenetic tree (i.e. language family tree) to identify top-k nearest languages for which we have training sets. Then we run models of those languages to obtain a hypothesis set, which we combine into a confusion network to propose a most likely hypothesis as an approximation to the target language. We test our approach on over 600 unseen languages and demonstrate it significantly outperforms baselines.

Combining the visual modality with pretrained language models has been surprisingly effective for simple descriptive tasks such as image captioning. More general text generation however remains elusive. We take a step back and ask: How do these models work for more complex generative tasks, i.e. conditioning on both text and images? Are multimodal models simply visually adapted language models, or do they combine they reason jointly over modalities?We investigate these questions in the context of self-rationalization (jointly generating task labels/answers and free-text explanations) of three tasks: (i) visual question answering in VQA-X, (ii) visual commonsense reasoning in VCR, and (iii) visual-textual entailment in E-SNLI-VE. We show that recent unimodal advances, CLIP image representations and scaling of language models, do not consistently improveself-rationalization in multimodal tasks. We find that no single model type works universally best across tasks, datasets, and finetuning data sizes. Our findings motivate the need for novel general backbones that move text generation from images and text beyond image captioning.

End-to-end spoken language understanding (SLU) systems are gaining popularity over cascaded approaches due to their simplicity and ability to avoid error propagation. However, these systems model sequence labeling as a sequence prediction task causing a divergence from its well-established token-level tagging formulation. We build compositional end-to-end SLU systems that explicitly separate the added complexity of recognizing spoken mentions in SLU from the NLU task of sequence labeling. By relying on intermediate decoders trained for ASR, our end-to-end systems transform the input modality from speech to token-level representations that can be used in the traditional sequence labeling framework. This composition of ASR and NLU formulations in our end-to-end SLU system offers direct compatibility with pre-trained ASR and NLU systems, allows performance monitoring of individual components and enables the use of globally normalized losses like CRF, making them attractive in practical scenarios. Our models outperform both cascaded and direct end-to-end models on a labeling task of named entity recognition across SLU benchmarks.

Sentiment analysis in Code-Mixed languages has garnered a lot of attention in recent years. It is an important task for social media monitoring and has many applications, as a large chunk of social media data is Code-Mixed. In this paper, we work on the problem of sentiment analysis for Dravidian Code-Switched languages - Tamil-Engish and Malayalam-English, using three different BERT based models. We leverage task-specific pre-training and cross-lingual transfer to improve on previously reported results, with significant improvement for the Tamil-Engish dataset. We also present a multilingual sentiment classification model that has competitive performance on both Tamil-English and Malayalam-English datasets.

When Question-Answering (QA) systems are deployed in the real world, users query them through a variety of interfaces, such as speaking to voice assistants, typing questions into a search engine, or even translating questions to languages supported by the QA system. While there has been significant community attention devoted to identifying correct answers in passages assuming a perfectly formed question, we show that components in the pipeline that precede an answering engine can introduce varied and considerable sources of error, and performance can degrade substantially based on these upstream noise sources even for powerful pre-trained QA models. We conclude that there is substantial room for progress before QA systems can be effectively deployed, highlight the need for QA evaluation to expand to consider real-world use, and hope that our findings will spur greater community interest in the issues that arise when our systems actually need to be of utility to humans.

Code-switching (CS), a ubiquitous phenomenon due to the ease of communication it offers in multilingual communities still remains an understudied problem in language processing. The primary reasons behind this are: (1) minimal efforts in leveraging large pretrained multilingual models, and (2) the lack of annotated data. The distinguishing case of low performance of multilingual models in CS is the intra-sentence mixing of languages leading to switch points. We first benchmark two sequence labeling tasks – POS and NER on 4 different language pairs with a suite of pretrained models to identify the problems and select the best performing char-BERT model among them (addressing (1)). We then propose a self training method to repurpose the existing pretrained models using a switch-point bias by leveraging unannotated data (addressing (2)). We finally demonstrate that our approach performs well on both tasks by reducing the gap between the switch point performance while retaining the overall performance on two distinct language pairs in both the tasks. We plan to release our models and the code for all our experiments.

Privacy plays a crucial role in preserving democratic ideals and personal autonomy. The dominant legal approach to privacy in many jurisdictions is the “Notice and Choice” paradigm, where privacy policies are the primary instrument used to convey information to users. However, privacy policies are long and complex documents that are difficult for users to read and comprehend. We discuss how language technologies can play an important role in addressing this information gap, reporting on initial progress towards helping three specific categories of stakeholders take advantage of digital privacy policies: consumers, enterprises, and regulators. Our goal is to provide a roadmap for the development and use of language technologies to empower users to reclaim control over their privacy, limit privacy harms, and rally research efforts from the community towards addressing an issue with large social impact. We highlight many remaining opportunities to develop language technologies that are more precise or nuanced in the way in which they use the text of privacy policies.

Recent work in natural language processing (NLP) has focused on ethical challenges such as understanding and mitigating bias in data and algorithms; identifying objectionable content like hate speech, stereotypes and offensive language; and building frameworks for better system design and data handling practices. However, there has been little discussion about the ethical foundations that underlie these efforts. In this work, we study one ethical theory, namely deontological ethics, from the perspective of NLP. In particular, we focus on the generalization principle and the respect for autonomy through informed consent. We provide four case studies to demonstrate how these principles can be used with NLP systems. We also recommend directions to avoid the ethical issues in these systems.

Document grounded generation is the task of using the information provided in a document to improve text generation. This work focuses on two different document grounded generation tasks: Wikipedia Update Generation task and Dialogue response generation. Our work introduces two novel adaptations of large scale pre-trained encoder-decoder models focusing on building context driven representation of the document and enabling specific attention to the information in the document. Additionally, we provide a stronger BART baseline for these tasks. Our proposed techniques outperform existing methods on both automated (at least 48% increase in BLEU-4 points) and human evaluation for closeness to reference and relevance to the document. Furthermore, we perform comprehensive manual inspection of the generated output and categorize errors to provide insights into future directions in modeling these tasks.

Sentiment analysis is an important task in understanding social media content like customer reviews, Twitter and Facebook feeds etc. In multilingual communities around the world, a large amount of social media text is characterized by the presence of Code-Switching. Thus, it has become important to build models that can handle code-switched data. However, annotated code-switched data is scarce and there is a need for unsupervised models and algorithms. We propose a general framework called Unsupervised Self-Training and show its applications for the specific use case of sentiment analysis of code-switched data. We use the power of pre-trained BERT models for initialization and fine-tune them in an unsupervised manner, only using pseudo labels produced by zero-shot transfer. We test our algorithm on multiple code-switched languages and provide a detailed analysis of the learning dynamics of the algorithm with the aim of answering the question - ‘Does our unsupervised model understand the Code-Switched languages or does it just learn its representations?’. Our unsupervised models compete well with their supervised counterparts, with their performance reaching within 1-7% (weighted F1 scores) when compared to supervised models trained for a two class problem.

The NLP community has witnessed steep progress in a variety of tasks across the realms of monolingual and multilingual language processing recently. These successes, in conjunction with the proliferating mixed language interactions on social media, have boosted interest in modeling code-mixed texts. In this work, we present CodemixedNLP, an open-source library with the goals of bringing together the advances in code-mixed NLP and opening it up to a wider machine learning community. The library consists of tools to develop and benchmark versatile model architectures that are tailored for mixed texts, methods to expand training sets, techniques to quantify mixing styles, and fine-tuned state-of-the-art models for 7 tasks in Hinglish. We believe this work has the potential to foster a distributed yet collaborative and sustainable ecosystem in an otherwise dispersed space of code-mixing research. The toolkit is designed to be simple, easily extensible, and resourceful to both researchers as well as practitioners. Demo: <http://k-ikkees.pc.cs.cmu.edu:5000> and Library: <https://github.com/murali1996/CodemixedNLP>

In this paper we describe our submission for the task of Propaganda Span Identification in news articles. We introduce a BERT-BiLSTM based span-level propaganda classification model that identifies which token spans within the sentence are indicative of propaganda. The ”multi-granular” model incorporates linguistic knowledge at various levels of text granularity, including word, sentence and document level syntactic, semantic and pragmatic affect features, which significantly improve model performance, compared to its language-agnostic variant. To facilitate better representation learning, we also collect a corpus of 10k news articles, and use it for fine-tuning the model. The final model is a majority-voting ensemble which learns different propaganda class boundaries by leveraging different subsets of incorporated knowledge.

Most natural language processing research now recommends large Transformer-based models with fine-tuning for supervised classification tasks; older strategies like bag-of-words features and linear models have fallen out of favor. Here we investigate whether, in automated essay scoring (AES) research, deep neural models are an appropriate technological choice. We find that fine-tuning BERT produces similar performance to classical models at significant additional cost. We argue that while state-of-the-art strategies do match existing best results, they come with opportunity costs in computational resources. We conclude with a review of promising areas for research on student essays where the unique characteristics of Transformers may provide benefits over classical methods to justify the costs.

Code-switching is a ubiquitous phenomenon in multilingual communities. Natural language technologies that wish to communicate like humans must therefore adaptively incorporate code-switching techniques when they are deployed in multilingual settings. To this end, we propose a Hindi-English human-machine dialogue system that elicits code-switching conversations in a controlled setting. It uses different code-switching agent strategies to understand how users respond and accommodate to the agent’s language choice. Through this system, we collect and release a new dataset CommonDost, comprising of 439 human-machine multilingual conversations. We adapt pre-defined metrics to discover linguistic accommodation from users to agents. Finally, we compare these dialogues with Spanish-English dialogues collected in a similar setting, and analyze the impact of linguistic and socio-cultural factors on code-switching patterns across the two language pairs.

This paper introduces a new task of politeness transfer which involves converting non-polite sentences to polite sentences while preserving the meaning. We also provide a dataset of more than 1.39 instances automatically labeled for politeness to encourage benchmark evaluations on this new task. We design a tag and generate pipeline that identifies stylistic attributes and subsequently generates a sentence in the target style while preserving most of the source content. For politeness as well as five other transfer tasks, our model outperforms the state-of-the-art methods on automatic metrics for content preservation, with a comparable or better performance on style transfer accuracy. Additionally, our model surpasses existing methods on human evaluations for grammaticality, meaning preservation and transfer accuracy across all the six style transfer tasks. The data and code is located at https://github.com/tag-and-generate.

End-to-end models for speech translation (ST) more tightly couple speech recognition (ASR) and machine translation (MT) than a traditional cascade of separate ASR and MT models, with simpler model architectures and the potential for reduced error propagation. Their performance is often assumed to be superior, though in many conditions this is not yet the case. We compare cascaded and end-to-end models across high, medium, and low-resource conditions, and show that cascades remain stronger baselines. Further, we introduce two methods to incorporate phone features into ST models. We show that these features improve both architectures, closing the gap between end-to-end models and cascades, and outperforming previous academic work – by up to 9 BLEU on our low-resource setting.

Sentence ordering is the task of arranging the sentences of a given text in the correct order. Recent work using deep neural networks for this task has framed it as a sequence prediction problem. In this paper, we propose a new framing of this task as a constraint solving problem and introduce a new technique to solve it. Additionally, we propose a human evaluation for this task. The results on both automatic and human metrics across four different datasets show that this new technique is better at capturing coherence in documents.

A major hurdle in data-driven research on typology is having sufficient data in many languages to draw meaningful conclusions. We present VoxClamantis v1.0, the first large-scale corpus for phonetic typology, with aligned segments and estimated phoneme-level labels in 690 readings spanning 635 languages, along with acoustic-phonetic measures of vowels and sibilants. Access to such data can greatly facilitate investigation of phonetic typology at a large scale and across many languages. However, it is non-trivial and computationally intensive to obtain such alignments for hundreds of languages, many of which have few to no resources presently available. We describe the methodology to create our corpus, discuss caveats with current methods and their impact on the utility of this data, and illustrate possible research directions through a series of case studies on the 48 highest-quality readings. Our corpus and scripts are publicly available for non-commercial use at https://voxclamantisproject.github.io.

Question answering and conversational systems are often baffled and need help clarifying certain ambiguities. However, limitations of existing datasets hinder the development of large-scale models capable of generating and utilising clarification questions. In order to overcome these limitations, we devise a novel bootstrapping framework (based on self-supervision) that assists in the creation of a diverse, large-scale dataset of clarification questions based on post-comment tuples extracted from stackexchange. The framework utilises a neural network based architecture for classifying clarification questions. It is a two-step method where the first aims to increase the precision of the classifier and second aims to increase its recall. We quantitatively demonstrate the utility of the newly created dataset by applying it to the downstream task of question-answering. The final dataset, ClarQ, consists of ~2M examples distributed across 173 domains of stackexchange. We release this dataset in order to foster research into the field of clarification question generation with the larger goal of enhancing dialog and question answering systems.

The presence of large-scale corpora for Natural Language Inference (NLI) has spurred deep learning research in this area, though much of this research has focused solely on monolingual data. Code-mixing is the intertwined usage of multiple languages, and is commonly seen in informal conversations among polyglots. Given the rising importance of dialogue agents, it is imperative that they understand code-mixing, but the scarcity of code-mixed Natural Language Understanding (NLU) datasets has precluded research in this area. The dataset by Khanuja et. al. for detecting conversational entailment in code-mixed Hindi-English text is the first of its kind. We investigate the effectiveness of language modeling, data augmentation, translation, and architectural approaches to address the code-mixed, conversational, and low-resource aspects of this dataset. We obtain an 8.09% increase in test set accuracy over the current state of the art.

We present a resource for computational experiments on Mapudungun, a polysynthetic indigenous language spoken in Chile with upwards of 200 thousand speakers. We provide 142 hours of culturally significant conversations in the domain of medical treatment. The conversations are fully transcribed and translated into Spanish. The transcriptions also include annotations for code-switching and non-standard pronunciations. We also provide baseline results on three core NLP tasks: speech recognition, speech synthesis, and machine translation between Spanish and Mapudungun. We further explore other applications for which the corpus will be suitable, including the study of code-switching, historical orthography change, linguistic structure, and sociological and anthropological studies.

We introduce a new resource, AlloVera, which provides mappings from 218 allophones to phonemes for 14 languages. Phonemes are contrastive phonological units, and allophones are their various concrete realizations, which are predictable from phonological context. While phonemic representations are language specific, phonetic representations (stated in terms of (allo)phones) are much closer to a universal (language-independent) transcription. AlloVera allows the training of speech recognition models that output phonetic transcriptions in the International Phonetic Alphabet (IPA), regardless of the input language. We show that a “universal” allophone model, Allosaurus, built with AlloVera, outperforms “universal” phonemic models and language-specific models on a speech-transcription task. We explore the implications of this technology (and related technologies) for the documentation of endangered and minority languages. We further explore other applications for which AlloVera will be suitable as it grows, including phonological typology.

Neural controllable text generation is an important area gaining attention due to its plethora of applications. Although there is a large body of prior work in controllable text generation, there is no unifying theme. In this work, we provide a new schema of the pipeline of the generation process by classifying it into five modules. The control of attributes in the generation process requires modification of these modules. We present an overview of different techniques used to perform the modulation of these modules. We also provide an analysis on the advantages and disadvantages of these techniques. We further pave ways to develop new architectures based on the combination of the modules described in this paper.

Generating long form narratives such as stories and procedures from multiple modalities has been a long standing dream for artificial intelligence. In this regard, there is often crucial subtext that is derived from the surrounding contexts. The general seq2seq training methods render the models shorthanded while attempting to bridge the gap between these neighbouring contexts. In this paper, we tackle this problem by using infilling techniques involving prediction of missing steps in a narrative while generating textual descriptions from a sequence of images. We also present a new large scale visual procedure telling (ViPT) dataset with a total of 46,200 procedures and around 340k pairwise images and textual descriptions that is rich in such contextual dependencies. Generating steps using infilling technique demonstrates the effectiveness in visual procedures with more coherent texts. We conclusively show a METEOR score of 27.51 on procedures which is higher than the state-of-the-art on visual storytelling. We also demonstrate the effects of interposing new text with missing images during inference. The code and the dataset will be publicly available at https://visual-narratives.github.io/Visual-Narratives/.

Online texts - across genres, registers, domains, and styles - are riddled with human stereotypes, expressed in overt or subtle ways. Word embeddings, trained on these texts, perpetuate and amplify these stereotypes, and propagate biases to machine learning models that use word embeddings as features. In this work, we propose a method to debias word embeddings in multiclass settings such as race and religion, extending the work of (Bolukbasi et al., 2016) from the binary setting, such as binary gender. Next, we propose a novel methodology for the evaluation of multiclass debiasing. We demonstrate that our multiclass debiasing is robust and maintains the efficacy in standard NLP tasks.

We consider neural language generation under a novel problem setting: generating the words of a sentence according to the order of their first appearance in its lexicalized PCFG parse tree, in a depth-first, left-to-right manner. Unlike previous tree-based language generation methods, our approach is both (i) top-down and (ii) explicitly generating syntactic structure at the same time. In addition, our method combines neural model with symbolic approach: word choice at each step is constrained by its predicted syntactic function. We applied our model to the task of dialog response generation, and found it significantly improves over sequence-to-sequence baseline, in terms of diversity and relevance. We also investigated the effect of lexicalization on language generation, and found that lexicalization schemes that give priority to content words have certain advantages over those focusing on dependency relations.

In group decision-making, the nuanced process of conflict and resolution that leads to consensus formation is closely tied to the quality of decisions made. Behavioral scientists rarely have rich access to process variables, though, as unstructured discussion transcripts are difficult to analyze. Here, we define ways for NLP researchers to contribute to the study of groups and teams. We introduce three tasks alongside a large new corpus of over 400,000 group debates on Wikipedia. We describe the tasks and their importance, then provide baselines showing that BERT contextualized word embeddings consistently outperform other language representations.

Visual storytelling is the task of generating stories based on a sequence of images. Inspired by the recent works in neural generation focusing on controlling the form of text, this paper explores the idea of generating these stories in different personas. However, one of the main challenges of performing this task is the lack of a dataset of visual stories in different personas. Having said that, there are independent datasets for both visual storytelling and annotated sentences for various persona. In this paper we describe an approach to overcome this by getting labelled persona data from a different task and leveraging those annotations to perform persona based story generation. We inspect various ways of incorporating personality in both the encoder and the decoder representations to steer the generation in the target direction. To this end, we propose five models which are incremental extensions to the baseline model to perform the task at hand. In our experiments we use five different personas to guide the generation process. We find that the models based on our hypotheses perform better at capturing words while generating stories in the target persona.

We study the problem of generating interesting endings for stories. Neural generative models have shown promising results for various text generation problems. Sequence to Sequence (Seq2Seq) models are typically trained to generate a single output sequence for a given input sequence. However, in the context of a story, multiple endings are possible. Seq2Seq models tend to ignore the context and generate generic and dull responses. Very few works have studied generating diverse and interesting story endings for the same story context. In this paper, we propose models which generate more diverse and interesting outputs by 1) training models to focus attention on important keyphrases of the story, and 2) promoting generating nongeneric words. We show that the combination of the two leads to more interesting endings.

We critique recent work on ethics in natural language processing. Those discussions have focused on data collection, experimental design, and interventions in modeling. But we argue that we ought to first understand the frameworks of ethics that are being used to evaluate the fairness and justice of algorithmic systems. Here, we begin that discussion by outlining deontological and consequentialist ethics, and make predictions on the research agenda prioritized by each.

Contextual word embeddings such as BERT have achieved state of the art performance in numerous NLP tasks. Since they are optimized to capture the statistical properties of training data, they tend to pick up on and amplify social stereotypes present in the data as well. In this study, we (1) propose a template-based method to quantify bias in BERT; (2) show that this method obtains more consistent results in capturing social biases than the traditional cosine based method; and (3) conduct a case study, evaluating gender bias in a downstream task of Gender Pronoun Resolution. Although our case study focuses on gender bias, the proposed technique is generalizable to unveiling other biases, including in multiclass settings, such as racial and religious biases.

There is a long record of research on equity in schools. As machine learning researchers begin to study fairness and bias in earnest, language technologies in education have an unusually strong theoretical and applied foundation to build on. Here, we introduce concepts from culturally relevant pedagogy and other frameworks for teaching and learning, identifying future work on equity in NLP. We present case studies in a range of topics like intelligent tutoring systems, computer-assisted language learning, automated essay scoring, and sentiment analysis in classrooms, and provide an actionable agenda for research.

Negotiation is a complex activity involving strategic reasoning, persuasion, and psychology. An average person is often far from an expert in negotiation. Our goal is to assist humans to become better negotiators through a machine-in-the-loop approach that combines machine’s advantage at data-driven decision-making and human’s language generation ability. We consider a bargaining scenario where a seller and a buyer negotiate the price of an item for sale through a text-based dialogue. Our negotiation coach monitors messages between them and recommends strategies in real time to the seller to get a better deal (e.g., “reject the proposal and propose a price”, “talk about your personal experience with the product”). The best strategy largely depends on the context (e.g., the current price, the buyer’s attitude). Therefore, we first identify a set of negotiation strategies, then learn to predict the best strategy in a given dialogue context from a set of human-human bargaining dialogues. Evaluation on human-human dialogues shows that our coach increases the profits of the seller by almost 60%.

Neural models have become one of the most important approaches to dialog response generation. However, they still tend to generate the most common and generic responses in the corpus all the time. To address this problem, we designed an iterative training process and ensemble method based on boosting. We combined our method with different training and decoding paradigms as the base model, including mutual-information-based decoding and reward-augmented maximum likelihood learning. Empirical results show that our approach can significantly improve the diversity and relevance of the responses generated by all base models, backed by objective measurements and human evaluation.

Previous work on end-to-end translation from speech has primarily used frame-level features as speech representations, which creates longer, sparser sequences than text. We show that a naive method to create compressed phoneme-like speech representations is far more effective and efficient for translation than traditional frame-level speech features. Specifically, we generate phoneme labels for speech frames and average consecutive frames with the same label to create shorter, higher-level source sequences for translation. We see improvements of up to 5 BLEU on both our high and low resource language pairs, with a reduction in training time of 60%. Our improvements hold across multiple data sizes and two language pairs.

Information need of humans is essentially multimodal in nature, enabling maximum exploitation of situated context. We introduce a dataset for sequential procedural (how-to) text generation from images in cooking domain. The dataset consists of 16,441 cooking recipes with 160,479 photos associated with different steps. We setup a baseline motivated by the best performing model in terms of human evaluation for the Visual Story Telling (ViST) task. In addition, we introduce two models to incorporate high level structure learnt by a Finite State Machine (FSM) in neural sequential generation process by: (1) Scaffolding Structure in Decoder (SSiD) (2) Scaffolding Structure in Loss (SSiL). Our best performing model (SSiL) achieves a METEOR score of 0.31, which is an improvement of 0.6 over the baseline model. We also conducted human evaluation of the generated grounded recipes, which reveal that 61% found that our proposed (SSiL) model is better than the baseline model in terms of overall recipes. We also discuss analysis of the output highlighting key important NLP issues for prospective directions.

Privacy policies are long and complex documents that are difficult for users to read and understand. Yet, they have legal effects on how user data can be collected, managed and used. Ideally, we would like to empower users to inform themselves about the issues that matter to them, and enable them to selectively explore these issues. We present PrivacyQA, a corpus consisting of 1750 questions about the privacy policies of mobile applications, and over 3500 expert annotations of relevant answers. We observe that a strong neural baseline underperforms human performance by almost 0.3 F1 on PrivacyQA, suggesting considerable room for improvement for future systems. Further, we use this dataset to categorically identify challenges to question answerability, with domain-general implications for any question answering system. The PrivacyQA corpus offers a challenging corpus for question answering, with genuine real world utility.

Typical datasets used for style transfer in NLP contain aligned pairs of two opposite extremes of a style. As each existing dataset is sourced from a specific domain and context, most use cases will have a sizable mismatch from the vocabulary and sentence structures of any dataset available. This reduces the performance of the style transfer, and is particularly significant for noisy, user-generated text. To solve this problem, we show a technique to derive a dataset of aligned pairs (style-agnostic vs stylistic sentences) from an unlabeled corpus by using an auxiliary dataset, allowing for in-domain training. We test the technique with the Yahoo Formality Dataset and 6 novel datasets we produced, which consist of scripts from 5 popular TV-shows (Friends, Futurama, Seinfeld, Southpark, Stargate SG-1) and the Slate Star Codex online forum. We gather 1080 human evaluations, which show that our method produces a sizable change in formality while maintaining fluency and context; and that it considerably outperforms OpenNMT’s Seq2Seq model directly trained on the Yahoo Formality Dataset. Additionally, we publish the full pipeline code and our novel datasets.

Irony detection is an important task with applications in identification of online abuse and harassment. With the ubiquitous use of non-verbal cues such as emojis in social media, in this work we aim to study the role of these structures in irony detection. Since the existing irony detection datasets have <10% ironic tweets with emoji, classifiers trained on them are insensitive to emojis. We propose an automated pipeline for creating a more balanced dataset.

Grapheme-to-phoneme conversion (g2p) is the task of predicting the pronunciation of words from their orthographic representation. His- torically, g2p systems were transition- or rule- based, making generalization beyond a mono- lingual (high resource) domain impractical. Recently, neural architectures have enabled multilingual systems to generalize widely; however, all systems to date have been trained only on spelling-pronunciation pairs. We hy- pothesize that the sequences of IPA characters used to represent pronunciation do not capture its full nuance, especially when cleaned to fa- cilitate machine learning. We leverage audio data as an auxiliary modality in a multi-task training process to learn a more optimal inter- mediate representation of source graphemes; this is the first multimodal model proposed for multilingual g2p. Our approach is highly ef- fective: on our in-domain test set, our mul- timodal model reduces phoneme error rate to 2.46%, a more than 65% decrease compared to our implementation of a unimodal spelling- pronunciation model—which itself achieves state-of-the-art results on the Wiktionary test set. The advantages of the multimodal model generalize to wholly unseen languages, reduc- ing phoneme error rate on our out-of-domain test set to 6.39% from the unimodal 8.21%, a more than 20% relative decrease. Further- more, our training and test sets are composed primarily of low-resource languages, demon- strating that our multimodal approach remains useful when training data are constrained.

Recent advances in deep learning have shown promises in solving complex combinatorial optimization problems, such as sorting variable-sized sequences. In this work, we take a step further and tackle the problem of ordering the elements of sequences that come with graph structures. Our solution adopts an encoder-decoder framework, in which the encoder is a graph neural network that learns the representation for each element, and the decoder predicts the ordering of each local neighborhood of the graph in turn. We apply our framework to multilingual surface realization, which is the task of ordering and completing sentences with their dependency parses given but without the ordering of words. Experiments show that our approach is much better for this task than prior works that do not consider graph structures. We participated in 2019 Surface Realization Shared Task (SR’19), and we ranked second out of 14 teams while outperforming those teams below by a large margin.

This paper introduces a document grounded dataset for conversations. We define “Document Grounded Conversations” as conversations that are about the contents of a specified document. In this dataset the specified documents were Wikipedia articles about popular movies. The dataset contains 4112 conversations with an average of 21.43 turns per conversation. This positions this dataset to not only provide a relevant chat history while generating responses but also provide a source of information that the models could use. We describe two neural architectures that provide benchmark performance on the task of generating the next response. We also evaluate our models for engagement and fluency, and find that the information from the document helps in generating more engaging and fluent responses.

Code-Mixing (CM) is the phenomenon of alternating between two or more languages which is prevalent in bi- and multi-lingual communities. Most NLP applications today are still designed with the assumption of a single interaction language and are most likely to break given a CM utterance with multiple languages mixed at a morphological, phrase or sentence level. For example, popular commercial search engines do not yet fully understand the intents expressed in CM queries. As a first step towards fostering research which supports CM in NLP applications, we systematically crowd-sourced and curated an evaluation dataset for factoid question answering in three CM languages - Hinglish (Hindi+English), Tenglish (Telugu+English) and Tamlish (Tamil+English) which belong to two language families (Indo-Aryan and Dravidian). We share the details of our data collection process, techniques which were used to avoid inducing lexical bias amongst the crowd workers and other CM specific linguistic properties of the dataset. Our final dataset, which is available freely for research purposes, has 1,694 Hinglish, 2,848 Tamlish and 1,391 Tenglish factoid questions and their answers. We discuss the techniques used by the participants for the first edition of this ongoing challenge.

Multilingual speakers switch between languages in an non-trivial fashion displaying inter sentential, intra sentential, and congruent lexicalization based transitions. While monolingual ASR systems may be capable of recognizing a few words from a foreign language, they are usually not robust enough to handle these varied styles of code-switching. There is also a lack of large code-switched speech corpora capturing all these styles making it difficult to build code-switched speech recognition systems. We hypothesize that it may be useful for an ASR system to be able to first detect the switching style of a particular utterance from acoustics, and then use specialized language models or other adaptation techniques for decoding the speech. In this paper, we look at the first problem of detecting code-switching style from acoustics. We classify code-switched Spanish-English and Hindi-English corpora using two metrics and show that features extracted from acoustics alone can distinguish between different kinds of code-switching in these language pairs.

Code-switching (CS), the practice of alternating between two or more languages in conversations, is pervasive in most multi-lingual communities. CS texts have a complex interplay between languages and occur in informal contexts that make them harder to collect and construct NLP tools for. We approach this problem through Language Modeling (LM) on a new Hindi-English mixed corpus containing 59,189 unique sentences collected from blogging websites. We implement and discuss different Language Models derived from a multi-layered LSTM architecture. We hypothesize that encoding language information strengthens a language model by helping to learn code-switching points. We show that our highest performing model achieves a test perplexity of 19.52 on the CS corpus that we collected and processed. On this data we demonstrate that our performance is an improvement over AWD-LSTM LM (a recent state of the art on monolingual English).

Named Entity Recognition plays a major role in several downstream applications in NLP. Though this task has been heavily studied in formal monolingual texts and also noisy texts like Twitter data, it is still an emerging task in code-switched (CS) content on social media. This paper describes our participation in the shared task of NER on code-switched data for Spanglish (Spanish + English) and Arabish (Arabic + English). In this paper we describe models that intuitively developed from the data for the shared task Named Entity Recognition on Code-switched Data. Owing to the sparse and non-linear relationships between words in Twitter data, we explored neural architectures that are capable of non-linearities fairly well. In specific, we trained character level models and word level models based on Bidirectional LSTMs (Bi-LSTMs) to perform sequential tagging. We train multiple models to identify nominal mentions and subsequently use this information to predict the labels of named entity in a sequence. Our best model is a character level model along with word level pre-trained multilingual embeddings that gave an F-score of 56.72 in Spanglish and a word level model that gave an F-score of 65.02 in Arabish on the test data.

When creating a dialog system, developers need to test each version to ensure that it is performing correctly. Recently the trend has been to test on large datasets or to ask many users to try out a system. Crowdsourcing has solved the issue of finding users, but it presents new challenges such as how to use a crowdsourcing platform and what type of test is appropriate. DialCrowd has been designed to make system assessment easier and to ensure the quality of the result. This paper describes DialCrowd, what specific needs it fulfills and how it works. It then relates a test of DialCrowd by a group of dialog system developer.

Self-disclosure is a key social strategy employed in conversation to build relations and increase conversational depth. It has been heavily studied in psychology and linguistic literature, particularly for its ability to induce self-disclosure from the recipient, a phenomena known as reciprocity. However, we know little about how self-disclosure manifests in conversation with automated dialog systems, especially as any self-disclosure on the part of a dialog system is patently disingenuous. In this work, we run a large-scale quantitative analysis on the effect of self-disclosure by analyzing interactions between real-world users and a spoken dialog system in the context of social conversation. We find that indicators of reciprocity occur even in human-machine dialog, with far-reaching implications for chatbots in a variety of domains including education, negotiation and social dialog.

Data augmentation seeks to manipulate the available data for training to improve the generalization ability of models. We investigate two data augmentation proxies, permutation and flipping, for neural dialog response selection task on various models over multiple datasets, including both Chinese and English languages. Different from standard data augmentation techniques, our method combines the original and synthesized data for prediction. Empirical results show that our approach can gain 1 to 3 recall-at-1 points over baseline models in both full-scale and small-scale settings.

Style transfer is the task of rephrasing the text to contain specific stylistic properties without changing the intent or affect within the context. This paper introduces a new method for automatic style transfer. We first learn a latent representation of the input sentence which is grounded in a language translation model in order to better preserve the meaning of the sentence while reducing stylistic properties. Then adversarial generation techniques are used to make the output match the desired style. We evaluate this technique on three different style transformations: sentiment, gender and political slant. Compared to two state-of-the-art style transfer modeling techniques we show improvements both in automatic evaluation of style transfer and in manual evaluation of meaning preservation and fluency.

There has been a long standing interest in understanding ‘Social Influence’ both in Social Sciences and in Computational Linguistics. In this paper, we present a novel approach to study and measure interpersonal influence in daily interactions. Motivated by the basic principles of influence, we attempt to identify indicative linguistic features of the posts in an online knitting community. We present the scheme used to operationalize and label the posts as influential or non-influential. Experiments with the identified features show an improvement in the classification accuracy of influence by 3.15%. Our results illustrate the important correlation between the structure of the language and its potential to influence others.

Most Text to Speech (TTS) systems today assume that the input text is in a single language and is written in the same language that the text needs to be synthesized in. However, in bilingual and multilingual communities, code mixing or code switching occurs in speech, in which speakers switch between languages in the same utterance. Due to the popularity of social media, we now see code-mixing even in text in these multilingual communities. TTS systems capable of synthesizing such text need to be able to handle text that is written in multiple languages and scripts. Code-mixed text poses many challenges to TTS systems, such as language identification, spelling normalization and pronunciation modeling. In this work, we describe a preliminary framework for synthesizing code-mixed text. We carry out experiments on synthesizing code-mixed Hindi and English text. We find that there is a significant user preference for TTS systems that can correctly identify and pronounce words in different languages.

Writing intended to inform frequently contains references to document entities (DEs), a mixed class that includes orthographically structured items (e.g., illustrations, sections, lists) and discourse entities (arguments, suggestions, points). Such references are vital to the interpretation of documents, but they often eschew identifiers such as “Figure 1” for inexplicit phrases like “in this figure” or “from these premises”. We examine inexplicit references to DEs, termed DE references, and recast the problem of their automatic detection into the determination of relevant word senses. We then show the feasibility of machine learning for the detection of DE-relevant word senses, using a corpus of human-labeled synsets from WordNet. We test cross-domain performance by gathering lemmas and synsets from three corpora: website privacy policies, Wikipedia articles, and Wikibooks textbooks. Identifying DE references will enable language technologies to use the information encoded by them, permitting the automatic generation of finely-tuned descriptions of DEs and the presentation of richly-structured information to readers.

The current practice in virtual human dialogue systems is to use professional human recordings or limited-domain speech synthesis. Both approaches lead to good performance but at a high cost. To determine the best trade-off between performance and cost, we perform a systematic evaluation of human and synthesized voices with regard to naturalness, conversational aspect, and likability. We vary the type (in-domain vs. out-of-domain), length, and content of utterances, and take into account the age and native language of raters as well as their familiarity with speech synthesis. We present detailed results from two studies, a pilot one and one run on Amazon's Mechanical Turk. Our results suggest that a professional human voice can supersede both an amateur human voice and synthesized voices. Also, a high-quality general-purpose voice or a good limited-domain voice can perform better than amateur human recordings. We do not find any significant differences between the performance of a high-quality general-purpose voice and a limited-domain voice, both trained with speech recorded by actors. As expected, the high-quality general-purpose voice is rated higher than the limited-domain voice for out-of-domain sentences and lower for in-domain sentences. There is also a trend for long or negative-content utterances to receive lower ratings.

This work describes a process to extract Named Entity (NE) translations from the text available in web links (anchor texts). It translates a NE by retrieving a list of web documents in the target language, extracting the anchor texts from the links to those documents and finding the best translation from the anchor texts, using a combination of features, some of which, are specific to anchor texts. Experiments performed on a manually built corpora, suggest that over 70% of the NEs, ranging from unpopular to popular entities, can be translated correctly using sorely anchor texts. Tests on a Machine Translation task indicate that the system can be used to improve the quality of the translations of state-of-the-art statistical machine translation systems.

In this paper, we describe NineOneOne (9-1-1), a system designed to recognize and translate Spanish emergency calls for better dispatching. We analyze the research challenges in adapting speech translation technology to 9-1-1 domain. We report our initial research towards building the system and the results of our initial experiments.

The paper describes our portable two-way speech-to-speech translation system using a completely eyes-free/hands-free user interface. This system translates between the language pair English and Iraqi Arabic as well as between English and Farsi, and was built within the framework of the DARPA TransTac program. The Farsi language support was developed within a 90-day period, testing our ability to rapidly support new languages. The paper gives an overview of the system’s components along with the individual component objective measures and a discussion of issues relevant for the overall usage of the system. We found that usability, flexibility, and robustness serve as severe constraints on system architecture and design.

This paper describes the conversion of a set of feature grammar rules into a deterministic finite state machine that accepts the same language (or at least a well-defined related language). First the reasoning behind why this is an interesting thing to do within the Edinburgh speech recogniser project, is discussed. Then details about the compilation algorithm are given. Finally, there is some discussion of the advantages and disadvantages of this method of implementing feature based grammar formalisms.