82 citations · 486 across the 40 of their papers we have counts for
50 papers
Beyond Fresh Starts: Stateful Inference for Streaming ASR in Conversational Voice Agents
Sameep Chattopadhyay, Alexander Erdmann, Mari Ostendorf
Modern voice-agent systems rely on streaming speech recognition models that operate under stringent latency constraints. This study shows that, due to the limited memory constraint…
Does Collaborative Human-LM Dialogue Generation Help Information Extraction from Human Dialogues?
Bo-Ru Lu, Nikita Haduong, Chia-Hsuan Lee +7
The capabilities of pretrained language models have opened opportunities to explore new application areas, but applications involving human-human interaction are limited by the fac…
Building blocks for complex tasks: Robust generative event extraction for radiology reports under domain shifts
Sitong Zhou, Meliha Yetisgen, Mari Ostendorf
This paper explores methods for extracting information from radiology reports that generalize across exam modalities to reduce requirements for annotated data. We demonstrate that…
Fine-Grained Human Feedback Gives Better Rewards for Language Model Training
Zeqiu Wu, Yushi Hu, Weijia Shi +6
Language models (LMs) often exhibit undesirable text generation behaviors, including generating false, toxic, or irrelevant outputs. Reinforcement learning from human feedback (RLH…
TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering
Yushi Hu, Benlin Liu, Jungo Kasai +4
Despite thousands of researchers, engineers, and artists actively working on improving text-to-image generation models, systems often fail to produce images that accurately align w…
One Embedder, Any Task: Instruction-Finetuned Text Embeddings
Hongjin Su, Weijia Shi, Jungo Kasai +7
We introduce INSTRUCTOR, a new method for computing text embeddings given task instructions: every text input is embedded together with instructions explaining the use case (e.g.,…
Selective Annotation Makes Language Models Better Few-Shot Learners
Hongjin Su, Jungo Kasai, Chen Henry Wu +8
Many recent approaches to natural language tasks are built on the remarkable abilities of large language models. Large language models can perform in-context learning, where they l…
Generalizing through Forgetting -- Domain Generalization for Symptom Event Extraction in Clinical Notes
Sitong Zhou, Kevin Lybarger, Meliha Yetisgen +1
Symptom information is primarily documented in free-text clinical notes and is not directly accessible for downstream applications. To address this challenge, information extractio…
INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions
Zeqiu Wu, Ryu Parish, Hao Cheng +4
In an information-seeking conversation, a user may ask questions that are under-specified or unanswerable. An ideal agent would interact by initiating different response types acco…
Unsupervised Learning of Hierarchical Conversation Structure
Bo-Ru Lu, Yushi Hu, Hao Cheng +2
Human conversations can evolve in many different ways, creating challenges for automatic understanding and summarization. Goal-oriented conversations often have meaningful sub-dial…
Automatic Dialect Density Estimation for African American English
Alexander Johnson, Kevin Everson, Vijay Ravi +3
In this paper, we explore automatic prediction of dialect density of the African American English (AAE) dialect, where dialect density is defined as the percentage of words in an u…
In-Context Learning for Few-Shot Dialogue State Tracking
Yushi Hu, Chia-Hsuan Lee, Tianbao Xie +3
Collecting and annotating task-oriented dialogues is time-consuming and costly; thus, zero and few shot learning could greatly benefit dialogue state tracking (DST). In this work,…
Dialogue State Tracking with a Language Model using Schema-Driven Prompting
Chia-Hsuan Lee, Hao Cheng, Mari Ostendorf
Task-oriented conversational systems often use dialogue state tracking to represent the user's intentions, which involves filling in values of pre-defined slots. Many approaches ha…
DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization
Zeqiu Wu, Bo-Ru Lu, Hannaneh Hajishirzi +1
Identifying relevant knowledge to be used in conversational systems that are grounded in long documents is critical to effective response generation. We introduce a knowledge ident…
Assessing the Use of Prosody in Constituency Parsing of Imperfect Transcripts
Trang Tran, Mari Ostendorf
This work explores constituency parsing on automatically recognized transcripts of conversational speech. The neural parser is based on a sentence encoder that leverages word vecto…
Representations for Question Answering from Documents with Tables and Text
Vicky Zayats, Kristina Toutanova, Mari Ostendorf
Tables in Web documents are pervasive and can be directly used to answer many of the queries searched on the Web, motivating their integration in question answering. Very often inf…
Analysis of Disfluency in Children's Speech
Trang Tran, Morgan Tinkler, Gary Yeung +2
Disfluencies are prevalent in spontaneous speech, as shown in many studies of adult speech. Less is understood about children's speech, especially in pre-school children who are st…
On the Role of Style in Parsing Speech with Neural Models
Trang Tran, Jiahong Yuan, Yang Liu +1
The differences in written text and conversational speech are substantial; previous parsers trained on treebanked text have given very poor results on spontaneous speech. For spoke…
Extracting Summary Knowledge Graphs from Long Documents
Zeqiu Wu, Rik Koncel-Kedziorski, Mari Ostendorf +1
Knowledge graphs capture entities and relations from long documents and can facilitate reasoning in many downstream applications. Extracting compact knowledge graphs containing onl…
A Controllable Model of Grounded Response Generation
Zeqiu Wu, Michel Galley, Chris Brockett +8
Current end-to-end neural conversation models inherently lack the flexibility to impose semantic control in the response generation process, often resulting in uninteresting respon…
Annotating Social Determinants of Health Using Active Learning, and Characterizing Determinants Using Neural Event Extraction
Kevin Lybarger, Mari Ostendorf, Meliha Yetisgen
Social determinants of health (SDOH) affect health outcomes, and knowledge of SDOH can inform clinical decision-making. Automatically extracting SDOH information from clinical text…
Disfluencies and Human Speech Transcription Errors
Vicky Zayats, Trang Tran, Richard Wright +2
This paper explores contexts associated with errors in transcrip-tion of spontaneous speech, shedding light on human perceptionof disfluencies and other conversational speech pheno…
Giving Attention to the Unexpected: Using Prosody Innovations in Disfluency Detection
Vicky Zayats, Mari Ostendorf
Disfluencies in spontaneous speech are known to be associated with prosodic disruptions. However, most algorithms for disfluency detection use only word transcripts. Integrating pr…
A General Framework for Information Extraction using Dynamic Span Graphs
Yi Luan, Dave Wadden, Luheng He +3
We introduce a general framework for several information extraction tasks that share span representations using dynamically constructed span graphs. The graphs are constructed by s…