Online Gender-Based Violence is an increasing problem, but existing datasets fail to capture the plurality of possible annotator perspectives or ensure representation of affected groups. In a pilot study, we revisit the annotation of a widely used dataset to investigate the relationship between annotator identities and underlying attitudes and the responses they give to a sexism labelling task. We collect demographic and attitudinal information about crowd-sourced annotators using two validated surveys from Social Psychology. While we do not find any correlation between underlying attitudes and annotation behaviour, ethnicity does appear to be related to annotator responses for this pool of crowd-workers. We also conduct initial classification experiments using Large Language Models, finding that a state-of-the-art model trained with human feedback benefits from our broad data collection to perform better on the new labels. This study represents the initial stages of a wider data collection project, in which we aim to develop a taxonomy of GBV in partnership with affected stakeholders.

Pretrained language models (PLMs) for data-to-text (D2T) generation can use human-readable data labels such as column headings, keys, or relation names to generalize to out-of-domain examples. However, the models are well-known in producing semantically inaccurate outputs if these labels are ambiguous or incomplete, which is often the case in D2T datasets. In this paper, we expose this issue on the task of descibing a relation between two entities. For our experiments, we collect a novel dataset for verbalizing a diverse set of 1,522 unique relations from three large-scale knowledge graphs (Wikidata, DBPedia, YAGO). We find that although PLMs for D2T generation expectedly fail on unclear cases, models trained with a large variety of relation labels are surprisingly robust in verbalizing novel, unseen relations. We argue that using data with a diverse set of clear and meaningful labels is key to training D2T generation systems capable of generalizing to novel domains.

The ability to handle miscommunication is crucial to robust and faithful conversational AI. People usually deal with miscommunication immediately as they detect it, using highly systematic interactional mechanisms called repair. One important type of repair is Third Position Repair (TPR) whereby a speaker is initially misunderstood but then corrects the misunderstanding as it becomes apparent after the addressee’s erroneous response. Here, we collect and publicly release REPAIR-QA, the first large dataset of TPRs in a conversational question answering (QA) setting. The data is comprised of the TPR turns, corresponding dialogue contexts, and candidate repairs of the original turn for execution of TPRs. We demonstrate the usefulness of the data by training and evaluating strong baseline models for executing TPRs. For stand-alone TPR execution, we perform both automatic and human evaluations on a fine-tuned T5 model, as well as OpenAI’s GPT-3 LLMs. Additionally, we extrinsically evaluate the LLMs’ TPR processing capabilities in the downstream conversational QA task. The results indicate poor out-of-the-box performance on TPR’s by the GPT-3 models, which then significantly improves when exposed to REPAIR-QA.

Interactive and embodied tasks pose at least two fundamental challenges to existing Vision & Language (VL) models, including 1) grounding language in trajectories of actions and observations, and 2) referential disambiguation. To tackle these challenges, we propose an Embodied MultiModal Agent (EMMA): a unified encoder-decoder model that reasons over images and trajectories, and casts action prediction as multimodal text generation. By unifying all tasks as text generation, EMMA learns a language of actions which facilitates transfer across tasks. Different to previous modular approaches with independently trained components, we use a single multitask model where each task contributes to goal completion. EMMA performs on par with similar models on several VL benchmarks and sets a new state-of-the-art performance (36.81% success rate) on the Dialog-guided Task Completion (DTC), a benchmark to evaluate dialog-guided agents in the Alexa Arena.

Large Language Models (LLMs) have successfully been applied to code generation tasks, raising the question of how well these models understand programming. Typical programming languages have invariances and equivariances in their semantics that human programmers intuitively understand and exploit, such as the (near) invariance to the renaming of identifiers. We show that LLMs not only fail to properly generate correct Python code when default function names are swapped, but some of them even become more confident in their incorrect predictions as the model size increases, an instance of the recently discovered phenomenon of Inverse Scaling, which runs contrary to the commonly observed trend of increasing prediction quality with increasing model size. Our findings indicate that, despite their astonishing typical-case performance, LLMs still lack a deep, abstract understanding of the content they manipulate, making them unsuitable for tasks that statistically deviate from their training data, and that mere scaling is not enough to achieve such capability.

Large language models are known to produce output which sounds fluent and convincing, but is also often wrong, e.g. “unfaithful” with respect to a rationale as retrieved from a knowledge base. In this paper, we show that task-based systems which exhibit certain advanced linguistic dialog behaviors, such as lexical alignment (repeating what the user said), are in fact preferred and trusted more, whereas other phenomena, such as pronouns and ellipsis are dis-preferred. We use open-domain question answering systems as our test-bed for task based dialog generation and compare several open- and closed-book models. Our results highlight the danger of systems that appear to be trustworthy by parroting user input while providing an unfaithful response.

Recent model editing techniques promise to mitigate the problem of memorizing false or outdated associations during LLM training. However, we show that these techniques can introduce large unwanted side effects which are not detected by existing specificity benchmarks. We extend the existing CounterFact benchmark to include a dynamic component and dub our benchmark CounterFact+. Additionally, we extend the metrics used for measuring specificity by a principled KL divergence-based metric. We use this improved benchmark to evaluate recent model editing techniques and find that they suffer from low specificity. Our findings highlight the need for improved specificity benchmarks that identify and prevent unwanted side effects.

Online Gender-Based Violence (GBV), such as misogynistic abuse is an increasingly prevalent problem that technological approaches have struggled to address. Through the lens of the GBV framework, which is rooted in social science and policy, we systematically review 63 available resources for automated identification of such language. We find the datasets are limited in a number of important ways, such as their lack of theoretical grounding and stakeholder input, static nature, and focus on certain media platforms. Based on this review, we recommend development of future resources rooted in sociological expertise andcentering stakeholder voices, namely GBV experts and people with lived experience of GBV.

There are two competing approaches for modelling annotator disagreement: distributional soft-labelling approaches (which aim to capture the level of disagreement) or modelling perspectives of individual annotators or groups thereof. We adapt a multi-task architecture which has previously shown success in modelling perspectives to evaluate its performance on the SEMEVAL Task 11. We do so by combining both approaches, i.e. predicting individual annotator perspectives as an interim step towards predicting annotator disagreement. Despite its previous success, we found that a multi-task approach performed poorly on datasets which contained distinct annotator opinions, suggesting that this approach may not always be suitable when modelling perspectives. Furthermore, our results explain that while strongly perspectivist approaches might not achieve state-of-the-art performance according to evaluation metrics used by distributional approaches, our approach allows for a more nuanced understanding of individual perspectives present in the data. We argue that perspectivist approaches are preferable because they enable decision makers to amplify minority views, and that it is important to re-evaluate metrics to reflect this goal.

We demonstrate EMMA, an embodied multimodal agent which has been developed for the Alexa Prize SimBot challenge. The agent acts within a 3D simulated environment for household tasks. EMMA is a unified and multimodal generative model aimed at solving embodied tasks. In contrast to previous work, our approach treats multiple multimodal tasks as a single multimodal conditional text generation problem, where a model learns to output text given both language and visual input. Furthermore, we showcase that a single generative agent can solve tasks with visual inputs of varying length, such as answering questions about static images, or executing actions given a sequence of previous frames and dialogue utterances. The demo system will allow users to interact conversationally with EMMA in embodied dialogues in different 3D environments from the TEACh dataset.

Automated Compliance Checking (ACC) systems aim to semantically parse building regulations to a set of rules. However, semantic parsing is known to be hard and requires large amounts of training data. The complexity of creating such training data has led to research that focuses on small sub-tasks, such as shallow parsing or the extraction of a limited subset of rules. This study introduces a shallow parsing task for which training data is relatively cheap to create, with the aim of learning a lexicon for ACC. We annotate a small domain-specific dataset of 200 sentences, SPaR.txt, and train a sequence tagger that achieves 79,93 F1-score on the test set. We then show through manual evaluation that the model identifies most (89,84%) defined terms in a set of building regulation documents, and that both contiguous and discontiguous Multi-Word Expressions (MWE) are discovered with reasonable accuracy (70,3%).

Guessing games are a prototypical instance of the “learning by interacting” paradigm. This work investigates how well an artificial agent can benefit from playing guessing games when later asked to perform on novel NLP downstream tasks such as Visual Question Answering (VQA). We propose two ways to exploit playing guessing games: 1) a supervised learning scenario in which the agent learns to mimic successful guessing games and 2) a novel way for an agent to play by itself, called Self-play via Iterated Experience Learning (SPIEL). We evaluate the ability of both procedures to generalise: an in-domain evaluation shows an increased accuracy (+7.79) compared with competitors on the evaluation suite CompGuessWhat?!; a transfer evaluation shows improved performance for VQA on the TDIUC dataset in terms of harmonic average accuracy (+5.31) thanks to more fine-grained object representations learned via SPIEL.

One of the most challenging aspects of current single-document news summarization is that the summary often contains ‘extrinsic hallucinations’, i.e., facts that are not present in the source document, which are often derived via world knowledge. This causes summarisation systems to act more like open-ended language models tending to hallucinate facts that are erroneous. In this paper, we mitigate this problem with the help of multiple supplementary resource documents assisting the task. We present a new dataset MiraNews and benchmark existing summarisation models. In contrast to multi-document summarization, which addresses multiple events from several source documents, we still aim at generating a summary for a single document. We show via data analysis that it’s not only the models which are to blame: more than 27% of facts mentioned in the gold summaries of MiraNews are better grounded on assisting documents than in the main source articles. An error analysis of generated summaries from pretrained models fine-tuned on MIRANEWS reveals that this has an even bigger effects on models: assisted summarisation reduces 55% of hallucinations when compared to single-document summarisation models trained on the main article only.

We present AggGen (pronounced ‘again’) a data-to-text model which re-introduces two explicit sentence planning stages into neural data-to-text systems: input ordering and input aggregation. In contrast to previous work using sentence planning, our model is still end-to-end: AggGen performs sentence planning at the same time as generating text by learning latent alignments (via semantic facts) between input representation and target text. Experiments on the WebNLG and E2E challenge data show that by using fact-based alignments our approach is more interpretable, expressive, robust to noise, and easier to control, while retaining the advantages of end-to-end systems in terms of fluency. Our code is available at https://github.com/XinnuoXu/AggGen.

Mixed initiative in open-domain dialogue requires a system to pro-actively introduce new topics. The one-turn topic transition task explores how a system connects two topics in a cooperative and coherent manner. The goal of the task is to generate a “bridging” utterance connecting the new topic to the topic of the previous conversation turn. We are especially interested in commonsense explanations of how a new topic relates to what has been mentioned before. We first collect a new dataset of human one-turn topic transitions, which we callOTTers. We then explore different strategies used by humans when asked to complete such a task, and notice that the use of a bridging utterance to connect the two topics is the approach used the most. We finally show how existing state-of-the-art text generation models can be adapted to this task and examine the performance of these baselines on different splits of the OTTers data.

Robust situated dialog requires the ability to process instructions based on spatial information, which may or may not be available. We propose a model, based on LXMERT, that can extract spatial information from text instructions and attend to landmarks on OpenStreetMap (OSM) referred to in a natural language instruction. Whilst, OSM is a valuable resource, as with any open-sourced data, there is noise and variation in the names referred to on the map, as well as, variation in natural language instructions, hence the need for data-driven methods over rule-based systems. This paper demonstrates that the gold GPS location can be accurately predicted from the natural language instruction and metadata with 72% accuracy for previously seen maps and 64% for unseen maps.

Nature has inspired various ground-breaking technological developments in applications ranging from robotics to aerospace engineering and the manufacturing of medical devices. However, accessing the information captured in scientific biology texts is a time-consuming and hard task that requires domain-specific knowledge. Improving access for outsiders can help interdisciplinary research like Nature Inspired Engineering. This paper describes a dataset of 1,500 manually-annotated sentences that express domain-independent relations between central concepts in a scientific biology text, such as trade-offs and correlations. The arguments of these relations can be Multi Word Expressions and have been annotated with modifying phrases to form non-projective graphs. The dataset allows for training and evaluating Relation Extraction algorithms that aim for coarse-grained typing of scientific biological documents, enabling a high-level filter for engineers.

Information Extraction (IE) from scientific texts can be used to guide readers to the central information in scientific documents. But narrow IE systems extract only a fraction of the information captured, and Open IE systems do not perform well on the long and complex sentences encountered in scientific texts. In this work we combine the output of both types of systems to achieve Semi-Open Relation Extraction, a new task that we explore in the Biology domain. First, we present the Focused Open Biological Information Extraction (FOBIE) dataset and use FOBIE to train a state-of-the-art narrow scientific IE system to extract trade-off relations and arguments that are central to biology texts. We then run both the narrow IE system and a state-of-the-art Open IE system on a corpus of 10K open-access scientific biological texts. We show that a significant amount (65%) of erroneous and uninformative Open IE extractions can be filtered using narrow IE extractions. Furthermore, we show that the retained extractions are significantly more often informative to a reader.

Abstractive summarisation is notoriously hard to evaluate since standard word-overlap-based metrics are insufficient. We introduce a new evaluation metric which is based on fact-level content weighting, i.e. relating the facts of the document to the facts of the summary. We fol- low the assumption that a good summary will reflect all relevant facts, i.e. the ones present in the ground truth (human-generated refer- ence summary). We confirm this hypothe- sis by showing that our weightings are highly correlated to human perception and compare favourably to the recent manual highlight- based metric of Hardy et al. (2019).

Approaches to Grounded Language Learning are commonly focused on a single task-based final performance measure which may not depend on desirable properties of the learned hidden representations, such as their ability to predict object attributes or generalize to unseen situations. To remedy this, we present GroLLA, an evaluation framework for Grounded Language Learning with Attributes based on three sub-tasks: 1) Goal-oriented evaluation; 2) Object attribute prediction evaluation; and 3) Zero-shot evaluation. We also propose a new dataset CompGuessWhat?! as an instance of this framework for evaluating the quality of learned neural representations, in particular with respect to attribute grounding. To this end, we extend the original GuessWhat?! dataset by including a semantic layer on top of the perceptual one. Specifically, we enrich the VisualGenome scene graphs associated with the GuessWhat?! images with several attributes from resources such as VISA and ImSitu. We then compare several hidden state representations from current state-of-the-art approaches to Grounded Language Learning. By using diagnostic classifiers, we show that current models’ learned representations are not expressive enough to encode object attributes (average F1 of 44.27). In addition, they do not learn strategies nor representations that are robust enough to perform well when novel scenes or objects are involved in gameplay (zero-shot best accuracy 50.06%).

Visual Dialogue involves “understanding” the dialogue history (what has been discussed previously) and the current question (what is asked), in addition to grounding information in the image, to accurately generate the correct response. In this paper, we show that co-attention models which explicitly encode dialoh history outperform models that don’t, achieving state-of-the-art performance (72 % NDCG on val set). However, we also expose shortcomings of the crowdsourcing dataset collection procedure, by showing that dialogue history is indeed only required for a small amount of the data, and that the current evaluation metric encourages generic replies. To that end, we propose a challenging subset (VisdialConv) of the VisdialVal set and the benchmark NDCG of 63%.

In visual guessing games, a Guesser has to identify a target object in a scene by asking questions to an Oracle. An effective strategy for the players is to learn conceptual representations of objects that are both discriminative and expressive enough to ask questions and guess correctly. However, as shown by Suglia et al. (2020), existing models fail to learn truly multi-modal representations, relying instead on gold category labels for objects in the scene both at training and inference time. This provides an unnatural performance advantage when categories at inference time match those at training time, and it causes models to fail in more realistic “zero-shot” scenarios where out-of-domain object categories are involved. To overcome this issue, we introduce a novel “imagination” module based on Regularized Auto-Encoders, that learns context-aware and category-aware latent embeddings without relying on category labels at inference time. Our imagination module outperforms state-of-the-art competitors by 8.26% gameplay accuracy in the CompGuessWhat?! zero-shot scenario (Suglia et al., 2020), and it improves the Oracle and Guesser accuracy by 2.08% and 12.86% in the GuessWhat?! benchmark, when no gold categories are available at inference time. The imagination module also boosts reasoning about object properties and attributes.

We describe the finding of the Fourth Workshop on Neural Generation and Translation, held in concert with the annual conference of the Association for Computational Linguistics (ACL 2020). First, we summarize the research trends of papers presented in the proceedings. Second, we describe the results of the three shared tasks 1) efficient neural machine translation (NMT) where participants were tasked with creating NMT systems that are both accurate and efficient, and 2) document-level generation and translation (DGT) where participants were tasked with developing systems that generate summaries from structured data, potentially with assistance from text in another language and 3) STAPLE task: creation of as many possible translations of a given input text. This last shared task was organised by Duolingo.

As autonomous systems become more commonplace, we need a way to easily and naturally communicate to them our goals and collaboratively come up with a plan on how to achieve these goals. To this end, we conducted a Wizard of Oz study to gather data and investigate the way operators would collaboratively make plans via a conversational ‘planning assistant’ for remote autonomous systems. We present here a corpus of 22 dialogs from expert operators, which can be used to train such a system. Data analysis shows that multimodality is key to successful interaction, measured both quantitatively and qualitatively via user feedback.

We present a recurrent neural network based system for automatic quality estimation of natural language generation (NLG) outputs, which jointly learns to assign numerical ratings to individual outputs and to provide pairwise rankings of two different outputs. The latter is trained using pairwise hinge loss over scores from two copies of the rating network. We use learning to rank and synthetic data to improve the quality of ratings assigned by our system: We synthesise training pairs of distorted system outputs and train the system to rank the less distorted one higher. This leads to a 12% increase in correlation with human ratings over the previous benchmark. We also establish the state of the art on the dataset of relative rankings from the E2E NLG Challenge (Dusek et al., 2019), where synthetic data lead to a 4% accuracy increase over the base model.

This document describes the findings of the Third Workshop on Neural Generation and Translation, held in concert with the annual conference of the Empirical Methods in Natural Language Processing (EMNLP 2019). First, we summarize the research trends of papers presented in the proceedings. Second, we describe the results of the two shared tasks 1) efficient neural machine translation (NMT) where participants were tasked with creating NMT systems that are both accurate and efficient, and 2) document generation and translation (DGT) where participants were tasked with developing systems that generate summaries from structured data, potentially with assistance from text in another language.

Neural sequence-to-sequence models are currently the dominant approach in several natural language processing tasks, but require large parallel corpora. We present a sequence-to-sequence-to-sequence autoencoder (SEQˆ3), consisting of two chained encoder-decoder pairs, with words used as a sequence of discrete latent variables. We apply the proposed model to unsupervised abstractive sentence compression, where the first and last sequences are the input and reconstructed sentences, respectively, while the middle sequence is the compressed sentence. Constraining the length of the latent word sequences forces the model to distill important information from the input. A pretrained language model, acting as a prior over the latent sequences, encourages the compressed sentences to be human-readable. Continuous relaxations enable us to sample from categorical distributions, allowing gradient-based optimization, unlike alternatives that rely on reinforcement learning. The proposed model does not require parallel text-summary pairs, achieving promising results in unsupervised sentence compression on benchmark datasets.

Source code is rarely written in isolation. It depends significantly on the programmatic context, such as the class that the code would reside in. To study this phenomenon, we introduce the task of generating class member functions given English documentation and the programmatic context provided by the rest of the class. This task is challenging because the desired code can vary greatly depending on the functionality the class provides (e.g., a sort function may or may not be available when we are asked to “return the smallest element” in a particular member variable list). We introduce CONCODE, a new large dataset with over 100,000 examples consisting of Java classes from online code repositories, and develop a new encoder-decoder architecture that models the interaction between the method documentation and the class environment. We also present a detailed error analysis suggesting that there is significant room for future work on this task.

We present three enhancements to existing encoder-decoder models for open-domain conversational agents, aimed at effectively modeling coherence and promoting output diversity: (1) We introduce a measure of coherence as the GloVe embedding similarity between the dialogue context and the generated response, (2) we filter our training corpora based on the measure of coherence to obtain topically coherent and lexically diverse context-response pairs, (3) we then train a response generator using a conditional variational autoencoder model that incorporates the measure of coherence as a latent variable and uses a context gate to guarantee topical consistency with the context and promote lexical diversity. Experiments on the OpenSubtitles corpus show a substantial improvement over competitive neural models in terms of BLEU score as well as metrics of coherence and diversity.

Multimodal search-based dialogue is a challenging new task: It extends visually grounded question answering systems into multi-turn conversations with access to an external database. We address this new challenge by learning a neural response generation system from the recently released Multimodal Dialogue (MMD) dataset (Saha et al., 2017). We introduce a knowledge-grounded multimodal conversational model where an encoded knowledge base (KB) representation is appended to the decoder input. Our model substantially outperforms strong baselines in terms of text-based similarity measures (over 9 BLEU points, 3 of which are solely due to the use of additional information from the KB).

In this work, we investigate the task of textual response generation in a multimodal task-oriented dialogue system. Our work is based on the recently released Multimodal Dialogue (MMD) dataset (Saha et al., 2017) in the fashion domain. We introduce a multimodal extension to the Hierarchical Recurrent Encoder-Decoder (HRED) model and show that this extension outperforms strong baselines in terms of text-based similarity metrics. We also showcase the shortcomings of current vision and language models by performing an error analysis on our system’s output.

Sequence-to-sequence models have shown strong performance across a broad range of applications. However, their application to parsing and generating text using Abstract Meaning Representation (AMR) has been limited, due to the relatively limited amount of labeled data and the non-sequential nature of the AMR graphs. We present a novel training procedure that can lift this limitation using millions of unlabeled sentences and careful preprocessing of the AMR graphs. For AMR parsing, our model achieves competitive results of 62.1 SMATCH, the current best score reported without significant use of external semantic resources. For AMR generation, our model establishes a new state-of-the-art performance of BLEU 33.8. We present extensive ablative and qualitative analysis including strong evidence that sequence-based AMR models are robust against ordering variations of graph-to-sequence conversions.

We present an approach to rapidly and easily build natural language interfaces to databases for new domains, whose performance improves over time based on user feedback, and requires minimal intervention. To achieve this, we adapt neural sequence models to map utterances directly to SQL with its full expressivity, bypassing any intermediate meaning representations. These models are immediately deployed online to solicit feedback from real users to flag incorrect queries. Finally, the popularity of SQL facilitates gathering annotations for incorrect predictions using the crowd, which is directly used to improve our models. This complete feedback loop, without intermediate representations or database specific engineering, opens up new ways of building high quality semantic parsers. Experiments suggest that this approach can be deployed quickly for any new target domain, as we show by learning a semantic parser for an online academic database from scratch.

This paper describes University of Washington NLP’s submission for the Linking Models of Lexical, Sentential and Discourse-level Semantics (LSDSem 2017) shared task—the Story Cloze Task. Our system is a linear classifier with a variety of features, including both the scores of a neural language model and style features. We report 75.2% accuracy on the task. A further discussion of our results can be found in Schwartz et al. (2017).

A writer’s style depends not just on personal traits but also on her intent and mental state. In this paper, we show how variants of the same writing task can lead to measurable differences in writing style. We present a case study based on the story cloze task (Mostafazadeh et al., 2016a), where annotators were assigned similar writing tasks with different constraints: (1) writing an entire story, (2) adding a story ending for a given story context, and (3) adding an incoherent ending to a story. We show that a simple linear classifier informed by stylistic features is able to successfully distinguish among the three cases, without even looking at the story context. In addition, combining our stylistic features with language model predictions reaches state of the art performance on the story cloze challenge. Our results demonstrate that different task framings can dramatically affect the way people write.