H. Wan, S. Patel, J. William Murdock, Saloni Potdar, Sachindra Joshi
{"title":"Fast and Light-Weight Answer Text Retrieval in Dialogue Systems","authors":"H. Wan, S. Patel, J. William Murdock, Saloni Potdar, Sachindra Joshi","doi":"10.48550/arXiv.2205.14226","DOIUrl":"https://doi.org/10.48550/arXiv.2205.14226","url":null,"abstract":"Dialogue systems can benefit from being able to search through a corpus of text to find information relevant to user requests, especially when encountering a request for which no manually curated response is available. The state-of-the-art technology for neural dense retrieval or re-ranking involves deep learning models with hundreds of millions of parameters. However, it is difficult and expensive to get such models to operate at an industrial scale, especially for cloud services that often need to support a big number of individually customized dialogue systems, each with its own text corpus. We report our work on enabling advanced neural dense retrieval systems to operate effectively at scale on relatively inexpensive hardware. We compare with leading alternative industrial solutions and show that we can provide a solution that is effective, fast, and cost-efficient.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116212721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Commonsense and Named Entity Aware Knowledge Grounded Dialogue Generation","authors":"Deeksha Varshney, Akshara Prabhakar, Asif Ekbal","doi":"10.48550/arXiv.2205.13928","DOIUrl":"https://doi.org/10.48550/arXiv.2205.13928","url":null,"abstract":"Grounding dialogue on external knowledge and interpreting linguistic patterns in dialogue history context, such as ellipsis, anaphora, and co-reference is critical for dialogue comprehension and generation. In this paper, we present a novel open-domain dialogue generation model which effectively utilizes the large-scale commonsense and named entity based knowledge in addition to the unstructured topic-specific knowledge associated with each utterance. We enhance the commonsense knowledge with named entity-aware structures using co-references. Our proposed model utilizes a multi-hop attention layer to preserve the most accurate and critical parts of the dialogue history and the associated knowledge. In addition, we employ a Commonsense and Named Entity Enhanced Attention Module, which starts with the extracted triples from various sources and gradually finds the relevant supporting set of triples using multi-hop attention with the query vector obtained from the interactive dialogue-knowledge module. Empirical results on two benchmark datasets demonstrate that our model significantly outperforms the state-of-the-art methods in terms of both automatic evaluation metrics and human judgment. Our code is publicly available at https://github.com/deekshaVarshney/CNTF; https://www.iitp.ac.in/-ai-nlp-ml/resources/codes/CNTF.zip.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115032214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhihan Zhou, Dejiao Zhang, Wei Xiao, Nicholas Dingwall, Xiaofei Ma, Andrew O. Arnold, Bing Xiang
{"title":"Learning Dialogue Representations from Consecutive Utterances","authors":"Zhihan Zhou, Dejiao Zhang, Wei Xiao, Nicholas Dingwall, Xiaofei Ma, Andrew O. Arnold, Bing Xiang","doi":"10.48550/arXiv.2205.13568","DOIUrl":"https://doi.org/10.48550/arXiv.2205.13568","url":null,"abstract":"Learning high-quality dialogue representations is essential for solving a variety of dialogue-oriented tasks, especially considering that dialogue systems often suffer from data scarcity. In this paper, we introduce Dialogue Sentence Embedding (DSE), a self-supervised contrastive learning method that learns effective dialogue representations suitable for a wide range of dialogue tasks. DSE learns from dialogues by taking consecutive utterances of the same dialogue as positive pairs for contrastive learning. Despite its simplicity, DSE achieves significantly better representation capability than other dialogue representation and universal sentence representation models. We evaluate DSE on five downstream dialogue tasks that examine dialogue representation at different semantic granularities. Experiments in few-shot and zero-shot settings show that DSE outperforms baselines by a large margin, for example, it achieves 13% average performance improvement over the strongest unsupervised baseline in 1-shot intent classification on 6 datasets. We also provide analyses on the benefits and limitations of our model.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"261 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122899542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Low Resource Style Transfer via Domain Adaptive Meta Learning","authors":"Xiangyang Li, Xiang Long, Yu Xia, Sujian Li","doi":"10.48550/arXiv.2205.12475","DOIUrl":"https://doi.org/10.48550/arXiv.2205.12475","url":null,"abstract":"Text style transfer (TST) without parallel data has achieved some practical success. However, most of the existing unsupervised text style transfer methods suffer from (i) requiring massive amounts of non-parallel data to guide transferring different text styles. (ii) colossal performance degradation when fine-tuning the model in new domains. In this work, we propose DAML-ATM (Domain Adaptive Meta-Learning with Adversarial Transfer Model), which consists of two parts: DAML and ATM. DAML is a domain adaptive meta-learning approach to learn general knowledge in multiple heterogeneous source domains, capable of adapting to new unseen domains with a small amount of data.Moreover, we propose a new unsupervised TST approach Adversarial Transfer Model (ATM), composed of a sequence-to-sequence pre-trained language model and uses adversarial style training for better content preservation and style transfer.Results on multi-domain datasets demonstrate that our approach generalizes well on unseen low-resource domains, achieving state-of-the-art results against ten strong baselines.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130172830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Partial-input baselines show that NLI models can ignore context, but they don’t.","authors":"Neha Srikanth, Rachel Rudinger","doi":"10.48550/arXiv.2205.12181","DOIUrl":"https://doi.org/10.48550/arXiv.2205.12181","url":null,"abstract":"When strong partial-input baselines reveal artifacts in crowdsourced NLI datasets, the performance of full-input models trained on such datasets is often dismissed as reliance on spurious correlations. We investigate whether state-of-the-art NLI models are capable of overriding default inferences made by a partial-input baseline. We introduce an evaluation set of 600 examples consisting of perturbed premises to examine a RoBERTa model’s sensitivity to edited contexts. Our results indicate that NLI models are still capable of learning to condition on context—a necessary component of inferential reasoning—despite being trained on artifact-ridden datasets.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124126628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hanhao Qu, Yu Cao, Jun Gao, Liang Ding, Ruifeng Xu
{"title":"Interpretable Proof Generation via Iterative Backward Reasoning","authors":"Hanhao Qu, Yu Cao, Jun Gao, Liang Ding, Ruifeng Xu","doi":"10.48550/arXiv.2205.10714","DOIUrl":"https://doi.org/10.48550/arXiv.2205.10714","url":null,"abstract":"We present IBR, an Iterative Backward Reasoning model to solve the proof generation tasks on rule-based Question Answering (QA), where models are required to reason over a series of textual rules and facts to find out the related proof path and derive the final answer. We handle the limitations of existed works in two folds: 1) enhance the interpretability of reasoning procedures with detailed tracking, by predicting nodes and edges in the proof path iteratively backward from the question; 2) promote the efficiency and accuracy via reasoning on the elaborate representations of nodes and history paths, without any intermediate texts that may introduce external noise during proof generation. There are three main modules in IBR, QA and proof strategy prediction to obtain the answer and offer guidance for the following procedure; parent node prediction to determine a node in the existing proof that a new child node will link to; child node prediction to find out which new node will be added to the proof. Experiments on both synthetic and paraphrased datasets demonstrate that IBR has better in-domain performance as well as cross-domain transferability than several strong baselines. Our code and models are available at https://github. com/find-knowledge/IBR.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128868803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Modeling Exemplification in Long-form Question Answering via Retrieval","authors":"Shufan Wang, Fangyuan Xu, Laure Thompson, Eunsol Choi, Mohit Iyyer","doi":"10.48550/arXiv.2205.09278","DOIUrl":"https://doi.org/10.48550/arXiv.2205.09278","url":null,"abstract":"Exemplification is a process by which writers explain or clarify a concept by providing an example. While common in all forms of writing, exemplification is particularly useful in the task of long-form question answering (LFQA), where a complicated answer can be made more understandable through simple examples. In this paper, we provide the first computational study of exemplification in QA, performing a fine-grained annotation of different types of examples (e.g., hypotheticals, anecdotes) in three corpora. We show that not only do state-of-the-art LFQA models struggle to generate relevant examples, but also that standard evaluation metrics such as ROUGE are insufficient to judge exemplification quality. We propose to treat exemplification as a retrieval problem in which a partially-written answer is used to query a large set of human-written examples extracted from a corpus. Our approach allows a reliable ranking-type automatic metrics that correlates well with human evaluation. A human evaluation shows that our model’s retrieved examples are more relevant than examples generated from a state-of-the-art LFQA model.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134376598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Penghui Wei, Xuanhua Yang, Shaoguo Liu, Liang Wang, Bo Zheng
{"title":"CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning","authors":"Penghui Wei, Xuanhua Yang, Shaoguo Liu, Liang Wang, Bo Zheng","doi":"10.48550/arXiv.2205.08943","DOIUrl":"https://doi.org/10.48550/arXiv.2205.08943","url":null,"abstract":"This paper focuses on automatically generating the text of an ad, and the goal is that the generated text can capture user interest for achieving higher click-through rate (CTR). We propose CREATER, a CTR-driven advertising text generation approach, to generate ad texts based on high-quality user reviews. To incorporate CTR objective, our model learns from online A/B test data with contrastive learning, which encourages the model to generate ad texts that obtain higher CTR. To make use of large-scale unpaired reviews, we design a customized self-supervised objective reducing the gap between pre-training and fine-tuning. Experiments on industrial datasets show that CREATER significantly outperforms current approaches. It has been deployed online in a leading advertising platform and brings uplift on core online metrics.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134572918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fedor Moiseev, Zhe Dong, Enrique Alfonseca, Martin Jaggi
{"title":"SKILL: Structured Knowledge Infusion for Large Language Models","authors":"Fedor Moiseev, Zhe Dong, Enrique Alfonseca, Martin Jaggi","doi":"10.18653/v1/2022.naacl-main.113","DOIUrl":"https://doi.org/10.18653/v1/2022.naacl-main.113","url":null,"abstract":"Large language models (LLMs) have demonstrated human-level performance on a vast spectrum of natural language tasks. However, it is largely unexplored whether they can better internalize knowledge from a structured data, such as a knowledge graph, or from text. In this work, we propose a method to infuse structured knowledge into LLMs, by directly training T5 models on factual triples of knowledge graphs (KGs). We show that models pre-trained on Wikidata KG with our method outperform the T5 baselines on FreebaseQA and WikiHop, as well as the Wikidata-answerable subset of TriviaQA and NaturalQuestions. The models pre-trained on factual triples compare competitively with the ones on natural language sentences that contain the same knowledge. Trained on a smaller size KG, WikiMovies, we saw 3x improvement of exact match score on MetaQA task. The proposed method has an advantage that no alignment between the knowledge graph and text corpus is required in curating training data. This makes our method particularly useful when working with industry-scale knowledge graphs.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132214215","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Generic and Trend-aware Curriculum Learning for Relation Extraction","authors":"Nidhi Vakil, Hadi Amiri","doi":"10.48550/arXiv.2205.08625","DOIUrl":"https://doi.org/10.48550/arXiv.2205.08625","url":null,"abstract":"We present a generic and trend-aware curriculum learning approach that effectively integrates textual and structural information in text graphs for relation extraction between entities, which we consider as node pairs in graphs. The proposed model extends existing curriculum learning approaches by incorporating sample-level loss trends to better discriminate easier from harder samples and schedule them for training. The model results in a robust estimation of sample difficulty and shows sizable improvement over the state-of-the-art approaches across several datasets.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133605524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}