Users of AI-based virtual assistants and search systems encounter challenges in articulating their intents while seeking information on unfamiliar topics, possibly due to complexity of the user’s intent or the lack of meta-information on the topic. We posit that an iterative suggested question-answering (SQA) conversation can improve the trade-off between the satisfaction of the user’s intent while keeping the information exchange natural and cognitive load of the interaction minimal on the users. In this paper, we evaluate a novel setting ProMISe by means of a sequence of interactions between a user, having a predefined information-seeking intent, and an agent that generates a set of SQA pairs at each step to aid the user to get closer to their intent. We simulate this two-player setting to create a multi-turn conversational dataset of SQAs and user choices (1025 dialogues comprising 4453 turns and 17812 SQAs) using human-feedback, chain-of-thought prompting and web-retrieval augmented large language models. We evaluate the quality of the SQs in the dataset on attributes such as diversity, specificity, grounding, etc, and benchmark the performance of different language models for the task of replicating user behavior.

Teaching large language models (LLMs) to generate text with attribution to evidence sources can reduce hallucinations, improve verifiability in question answering systems (QA), and increase reliability of retrieval augmented LLMs. Despite gaining increasing popularity for usage in QA systems and search engines, current LLMs struggle with attribution for long-form responses which require reasoning over multiple evidence sources. To address this, in this paper we aim to improve the attribution capability of LLMs for long-form answer generation to multiple sources, with multiple citations per sentence. However, data for training multi-source attributable QA systems is difficult and expensive to annotate, and therefore scarce. To overcome this challenge, we transform existing QA datasets for this task (MultiAttr), and empirically demonstrate, on a wide range of attribution benchmark datasets, that fine-tuning on MultiAttr provides significant improvements over training only on the target QA domain. Lastly, to fill a gap in existing benchmarks, we present a multi-source attribution dataset containing multi-paragraph answers, PolitiICite, based on PolitiFact articles that discuss events closely related to implementation statuses of election promises.

We propose CHRT (Control HiddenRepresentation Transformation) – a con-trolled language generation framework thatsteers large language models to generatetext pertaining to certain attributes (such astoxicity). CHRT gains attribute control bymodifying the hidden representation of thebase model through learned transformations. We employ a contrastive-learning frameworkto learn these transformations that can becombined to gain multi-attribute control. Theeffectiveness of CHRT is experimentallyshown by comparing it with seven baselinesover three attributes. CHRT outperforms all thebaselines in the task of detoxification, positivesentiment steering, and text simplificationwhile minimizing the loss in linguistic qualities. Further, our approach has the lowest inferencelatency of only 0.01 seconds more than thebase model, making it the most suitable forhigh-performance production environments. We open-source our code and release two noveldatasets to further propel controlled languagegeneration research

Meeting the expectations of e-commerce customers involves offering a seamless online shopping experience in their preferred language. To achieve this, modern e-commerce platforms rely on machine translation systems to provide multilingual product information on a large scale. However, maintaining high-quality machine translation that can keep up with the ever-expanding volume of product data remains an open challenge for industrial machine translation systems. In this context, topical clustering emerges as a valuable approach, leveraging latent signals and interpretable textual patterns to potentially enhance translation quality and facilitate industry-scale translation data discovery. This paper proposes two innovative methods: topic-based data selection and topic-signal augmentation, both utilizing latent topic clusters to improve the quality of machine translation in e-commerce. Furthermore, we present a data discovery workflow that utilizes topic clusters to effectively manage the growing multilingual product catalogs, addressing the challenges posed by their expansion.

Multilingual query localization is integral to modern e-commerce. While machine translation is widely used to translate e-commerce queries, evaluation of query translation in the context of the down-stream search task is overlooked. This study proposes a search ranking-based evaluation framework with an edit-distance based search metric to evaluate machine translation impact on cross-lingual information retrieval for e-commerce search query translation, The framework demonstrate evaluation of machine translation for e-commerce search at scale and the proposed metric is strongly associated with traditional machine translation and traditional search relevance-based metrics.

Previous work suggests that performance of cross-lingual information retrieval correlates highly with the quality of Machine Translation. However, there may be a threshold beyond which improving query translation quality yields little or no benefit to further improve the retrieval performance. This threshold may depend upon multiple factors including the source and target languages, the existing MT system quality and the search pipeline. In order to identify the benefit of improving an MT system for a given search pipeline, we investigate the sensitivity of retrieval quality to the presence of different levels of MT quality using experimental datasets collected from actual traffic. We systematically improve the performance of our MT systems quality on language pairs as measured by MT evaluation metrics including Bleu and Chrf to determine their impact on search precision metrics and extract signals that help to guide the improvement strategies. Using this information we develop techniques to compare query translations for multiple language pairs and identify the most promising language pairs to invest and improve.

Customers of machine learning systems demand accountability from the companies employing these algorithms for various prediction tasks. Accountability requires understanding of system limit and condition of erroneous predictions, as customers are often interested in understanding the incorrect predictions, and model developers are absorbed in finding methods that can be used to get incremental improvements to an existing system. Therefore, we propose an accountable error characterization method, AEC, to understand when and where errors occur within the existing black-box models. AEC, as constructed with human-understandable linguistic features, allows the model developers to automatically identify the main sources of errors for a given classification system. It can also be used to sample for the set of most informative input points for a next round of training. We perform error detection for a sentiment analysis task using AEC as a case study. Our results on the sample sentiment task show that AEC is able to characterize erroneous predictions into human understandable categories and also achieves promising results on selecting erroneous samples when compared with the uncertainty-based sampling.

Twitter customer service interactions have recently emerged as an effective platform to respond and engage with customers. In this work, we explore the role of ”negation” in customer service interactions, particularly applied to sentiment analysis. We define rules to identify true negation cues and scope more suited to conversational data than existing general review data. Using semantic knowledge and syntactic structure from constituency parse trees, we propose an algorithm for scope detection that performs comparable to state of the art BiLSTM. We further investigate the results of negation scope detection for the sentiment prediction task on customer service conversation data using both a traditional SVM and a Neural Network. We propose an antonym dictionary based method for negation applied to a combination CNN-LSTM for sentiment analysis. Experimental results show that the antonym-based method outperforms the previous lexicon-based and Neural Network methods.

Effective models of social dialog must understand a broad range of rhetorical and figurative devices. Rhetorical questions (RQs) are a type of figurative language whose aim is to achieve a pragmatic goal, such as structuring an argument, being persuasive, emphasizing a point, or being ironic. While there are computational models for other forms of figurative language, rhetorical questions have received little attention to date. We expand a small dataset from previous work, presenting a corpus of 10,270 RQs from debate forums and Twitter that represent different discourse functions. We show that we can clearly distinguish between RQs and sincere questions (0.76 F1). We then show that RQs can be used both sarcastically and non-sarcastically, observing that non-sarcastic (other) uses of RQs are frequently argumentative in forums, and persuasive in tweets. We present experiments to distinguish between these uses of RQs using SVM and LSTM models that represent linguistic features and post-level context, achieving results as high as 0.76 F1 for “sarcastic” and 0.77 F1 for “other” in forums, and 0.83 F1 for both “sarcastic” and “other” in tweets. We supplement our quantitative experiments with an in-depth characterization of the linguistic variation in RQs.