Papers by Mari Ostendorf
InSCIt: Information-Seeking Conversations with Mixed-Initiative Interactions (2023.tacl-1)
Copied to clipboard
Zeqiu Wu, Ryu Parish, Hao Cheng, Sewon Min, Prithviraj Ammanabrolu, Mari Ostendorf, Hannaneh Hajishirzi
| Challenge: | In information-seeking conversations, a user may ask questions that are under-specified or unanswerable. |
| Approach: | They present a dataset for information-seeking conversations with mixed-initiative interactions . they use Wikipedia to search for answers and provide relevant information . |
| Outcome: | The proposed system significantly underperforms humans in two of the most recent studies. |
CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning (2022.emnlp-main)
Copied to clipboard
Zeqiu Wu, Yi Luan, Hannah Rashkin, David Reitter, Hannaneh Hajishirzi, Mari Ostendorf, Gaurav Singh Tomar
| Challenge: | Existing models for conversational question answering require specific retrievers to understand user questions. |
| Approach: | They develop a query rewriting model CONQRR that rewrites a conversational question into a standalone question. |
| Outcome: | The proposed model achieves state-of-the-art on an open-domain conversational question answering dataset and is effective for two different off-the shelf retrievers. |
Unsupervised Learning of Hierarchical Conversation Structure (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Goal-oriented conversations often have sub-dialogue structure, but it can be domain-dependent . Increasingly, language understanding applications involve conversational speech and text . |
| Approach: | They propose an unsupervised approach to learning hierarchical conversation structure . they use turn and sub-dialogue segment labels to decode the structure based on dialogue acts and subtasks . |
| Outcome: | The proposed approach improves neural models for three conversation-level understanding tasks. |
A general framework for information extraction using dynamic span graphs (N19-1)
Copied to clipboard
| Challenge: | Existing frameworks for information extraction use a pipeline approach to identify entities and then use the detected entity spans for relation extraction and coreference resolution. |
| Approach: | They propose a framework for several information extraction tasks that share span representations using dynamically constructed span graphs. |
| Outcome: | The proposed framework significantly outperforms state-of-the-art on multiple information extraction tasks across multiple datasets reflecting different domains. |
Representations for Question Answering from Documents with Tables and Text (2021.eacl-main)
Copied to clipboard
| Challenge: | a study aims to improve question answering on tables by refining table representations based on textual context. |
| Approach: | They aim to improve question answering from tables by refining table representations based on textual context. |
| Outcome: | The proposed method improves on the Natural Questions dataset using text and table representations. |
Personalized Language Model for Query Auto-Completion (P18-2)
Copied to clipboard
| Challenge: | Query auto-completion (QAC) is a search engine feature that suggests completed queries as the user types . recent work suggests personalization of the recurrent layer to generate personalized completions. |
| Approach: | They propose to use a recurrent neural network language model to generate personalized completions for search engines. |
| Outcome: | The proposed model can generate personalized completions for users not seen during training. |
In-Context Learning for Few-Shot Dialogue State Tracking (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for zero-shot and few-shot learning dialogue state tracking are hard and expensive. |
| Approach: | They propose an in-context learning framework for zero-shot and few-shot learning dialogue state tracking (DST) a large pretrained language model takes a test instance and a few exemplars as input and directly decodes the dialogue state . |
| Outcome: | The proposed framework outperforms state-of-the-art models in few-shot settings . it is flexible and scalable, and requires less data to adapt to new domains and scenarios . |
DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge grounding models focus on locating knowledge in document contexts that are relevant to the conversation. |
| Approach: | They propose a knowledge identification model that leverages document structure to provide dialogue-contextualized passage encodings and better locate knowledge relevant to the conversation. |
| Outcome: | The proposed model can be applied to document-grounded conversational datasets and shows generalization to unseen documents and long dialogue contexts. |
Parsing Speech: a Neural Approach to Integrating Lexical and Acoustic-Prosodic Information (N18-1)
Copied to clipboard
| Challenge: | acoustic signals provide cues that help listeners disambiguate difficult parses . speech carries useful extra information associated with prosodic structure . |
| Approach: | They propose a model that integrates transcribed text and acoustic-prosodic features into a neural network that accepts text and prosodic feature. |
| Outcome: | The proposed model improves parse and disfluency detection scores over a strong text-only baseline. |
OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Tracking (2024.naacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are computationally expensive and often require computational resources. |
| Approach: | They propose a routing framework that seamlessly integrates a SLM and an LLM, or-lm, or a LLM into a single framework. |
| Outcome: | The proposed routing framework reduces the computational costs by over 50% in dialogue state tracking tasks. |
Community Member Retrieval on Social Media Using Textual Information (N18-2)
Copied to clipboard
| Challenge: | Existing methods for community membership detection using only text features are not effective. |
| Approach: | They propose an unsupervised task for learning user embeddings using text features . they propose a proxy task for embeddables that uses two embeddibles from the same account . |
| Outcome: | The proposed model is more effective than unsupervised representations of user embeddings with 16 different communities. |
One Embedder, Any Task: Instruction-Finetuned Text Embeddings (2023.findings-acl)
Copied to clipboard
Hongjin Su, Weijia Shi, Jungo Kasai, Yizhong Wang, Yushi Hu, Mari Ostendorf, Wen-tau Yih, Noah A. Smith, Luke Zettlemoyer, Tao Yu
| Challenge: | a new method for embedding text is developed for tasks that require specialized encoders . INSTRUCTOR is a single embedder that can generate text embeddables tailored to different tasks and domains based on instruction finetuning . |
| Approach: | They introduce a new method for computing text embeddings given task instructions . they first annotate instructions for 330 diverse tasks and train INSTRUCTOR on this multitask mixture . |
| Outcome: | The proposed method improves on 70 embedding evaluation tasks with fewer parameters than the previous best model. |
Privacy-preserving Prosody Representation Learning (2026.acl-short)
Copied to clipboard
| Challenge: | Acoustic-prosodic cues are known to carry speaker information, exposing users to privacy breaches . a new self-supervised learning approach addresses privacy concerns . |
| Approach: | They propose a self-supervised approach to learning prosody representations that incorporates speaker disentanglement strategies. |
| Outcome: | The proposed model outperforms raw prosody and HuBERT-base baselines on three tasks . it achieves strong speaker disentanglement without adverse impact on prosody-related downstream tasks compared with baselines . |
Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction (D18-1)
Copied to clipboard
| Challenge: | Existing relation extraction systems are designed for within-sentence relations, but extracting information from scientific articles requires relations across sentences. |
| Approach: | They propose a multi-task setup for identifying entities, relations, and coreference clusters in scientific articles . they develop a unified framework called SciIE with shared span representations to solve this problem . |
| Outcome: | The proposed model outperforms existing models without domain-specific features in scientific information extraction. |
Giving Attention to the Unexpected: Using Prosody Innovations in Disfluency Detection (N19-1)
Copied to clipboard
| Challenge: | Disfluencies in spontaneous speech are associated with prosodic disruptions. |
| Approach: | They propose a method to extract acoustic-prosodic cues from word transcripts . they explore early and late fusion techniques for integrating text and prosody . |
| Outcome: | The proposed approach shows gains over a high-accuracy text-only model. |
Dialogue State Tracking with a Language Model using Schema-Driven Prompting (2021.emnlp-main)
Copied to clipboard
| Challenge: | Task-oriented conversational systems often use dialogue state tracking to represent the user’s intentions, which involves filling in values of pre-defined slots. |
| Approach: | They propose a schema-driven prompting approach that provides task-aware history encoding that is used for both categorical and non-categorical slots. |
| Outcome: | The proposed system achieves state-of-the-art performance on MultiWOZ 2.2 and competitive performance on two other benchmarks: MultiWOz 2.1 and M2M. |
Sounding Board: A User-Centric and Content-Driven Social Chatbot (N18-5)
Copied to clipboard
Hao Fang, Hao Cheng, Maarten Sap, Elizabeth Clark, Ari Holtzman, Yejin Choi, Noah A. Smith, Mari Ostendorf
| Challenge: | Sounding Board is a social chatbot that can hold a coherent conversation with humans . the system is user-centric in that users can control the topic of conversation, while the system adapts to the user's needs. |
| Approach: | They present Sounding Board, a social chatbot that won the 2017 Amazon Alexa Prize. |
| Outcome: | The system is user-centric in that users can control the topic of conversation, while the system adapts to the user's needs. |
A Dynamic Speaker Model for Conversational Interactions (N19-1)
Copied to clipboard
| Challenge: | a neural model for characterizing individual differences in speakers is shown to be useful in human-computer interaction and dialog act prediction. |
| Approach: | They propose a neural model for learning a dynamically updated speaker embedding in a conversational context. |
| Outcome: | The proposed model is used for content ranking and dialog act prediction in human-human conversations. |