Sopan Khosla, Shikhar Vashishth, J. Lehman, C. Rosé
{"title":"Improving Detection and Categorization of Task-relevant Utterances through Integration of Discourse Structure and Ontological Knowledge","authors":"Sopan Khosla, Shikhar Vashishth, J. Lehman, C. Rosé","doi":"10.18653/v1/2020.emnlp-main.626","DOIUrl":"https://doi.org/10.18653/v1/2020.emnlp-main.626","url":null,"abstract":"Information extraction from conversational data is particularly challenging because the task-centric nature of conversation allows for effective communication of implicit information by humans, but is challenging for machines. The challenges may differ between utterances depending on the role of the speaker within the conversation, especially when relevant expertise is distributed asymmetrically across roles. Further, the challenges may also increase over the conversation as more shared context is built up through information communicated implicitly earlier in the dialogue. In this paper, we propose the novel modeling approach MedFilter, which addresses these insights in order to increase performance at identifying and categorizing task-relevant utterances, and in so doing, positively impacts performance at a downstream information extraction task. We evaluate this approach on a corpus of nearly 7,000 doctor-patient conversations where MedFilter is used to identify medically relevant contributions to the discussion (achieving a 10% improvement over SOTA baselines in terms of area under the PR curve). Identifying task-relevant utterances benefits downstream medical processing, achieving improvements of 15%, 105%, and 23% respectively for the extraction of symptoms, medications, and complaints.","PeriodicalId":320462,"journal":{"name":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130461179","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":"STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation","authors":"Nader Akoury, Shufan Wang, Josh Whiting, Stephen Hood, Nanyun Peng, Mohit Iyyer","doi":"10.18653/v1/2020.emnlp-main.525","DOIUrl":"https://doi.org/10.18653/v1/2020.emnlp-main.525","url":null,"abstract":"Systems for story generation are asked to produce plausible and enjoyable stories given an input context. This task is underspecified, as a vast number of diverse stories can originate from a single input. The large output space makes it difficult to build and evaluate story generation models, as (1) existing datasets lack rich enough contexts to meaningfully guide models, and (2) existing evaluations (both crowdsourced and automatic) are unreliable for assessing long-form creative text. To address these issues, we introduce a dataset and evaluation platform built from STORIUM, an online collaborative storytelling community. Our author-generated dataset contains 6K lengthy stories (125M tokens) with fine-grained natural language annotations (e.g., character goals and attributes) interspersed throughout each narrative, forming a robust source for guiding models. We evaluate language models fine-tuned on our dataset by integrating them onto STORIUM, where real authors can query a model for suggested story continuations and then edit them. Automatic metrics computed over these edits correlate well with both user ratings of generated stories and qualitative feedback from semi-structured user interviews. We release both the STORIUM dataset and evaluation platform to spur more principled research into story generation.","PeriodicalId":320462,"journal":{"name":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","volume":"abs/2010.01717 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129838205","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}
Jonathan Pilault, Raymond Li, Sandeep Subramanian, C. Pal
{"title":"On Extractive and Abstractive Neural Document Summarization with Transformer Language Models","authors":"Jonathan Pilault, Raymond Li, Sandeep Subramanian, C. Pal","doi":"10.18653/v1/2020.emnlp-main.748","DOIUrl":"https://doi.org/10.18653/v1/2020.emnlp-main.748","url":null,"abstract":"We present a method to produce abstractive summaries of long documents that exceed several thousand words via neural abstractive summarization. We perform a simple extractive step before generating a summary, which is then used to condition the transformer language model on relevant information before being tasked with generating a summary. We also show that this approach produces more abstractive summaries compared to prior work that employs a copy mechanism while still achieving higher ROUGE scores. We provide extensive comparisons with strong baseline methods, prior state of the art work as well as multiple variants of our approach including those using only transformers, only extractive techniques and combinations of the two. We examine these models using four different summarization tasks and datasets: arXiv papers, PubMed papers, the Newsroom and BigPatent datasets. We find that transformer based methods produce summaries with fewer n-gram copies, leading to n-gram copying statistics that are more similar to human generated abstracts. We include a human evaluation, finding that transformers are ranked highly for coherence and fluency, but purely extractive methods score higher for informativeness and relevance. We hope that these architectures and experiments may serve as strong points of comparison for future work. Note: The abstract above was collaboratively written by the authors and one of the models presented in this paper based on an earlier draft of this paper.","PeriodicalId":320462,"journal":{"name":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127469689","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}