Disentangling Online Chats with DAG-Structured LSTMs

• URL: http://arxiv.org/abs/2106.09024v1
• Date: Wed, 16 Jun 2021 18:00:00 GMT
• Title: Disentangling Online Chats with DAG-Structured LSTMs
• Authors: Duccio Pappadopulo, Lisa Bauer, Marco Farina, Ozan \.Irsoy, and Mohit Bansal
• Abstract summary: DAG-LSTMs are a generalization of Tree-LSTMs that can handle directed acyclic dependencies. We show that the novel model we propose achieves state of the art status on the task of recovering reply-to relations.
• Score: 55.33014148383343
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many modern messaging systems allow fast and synchronous textual communication among many users. The resulting sequence of messages hides a more complicated structure in which independent sub-conversations are interwoven with one another. This poses a challenge for any task aiming to understand the content of the chat logs or gather information from them. The ability to disentangle these conversations is then tantamount to the success of many downstream tasks such as summarization and question answering. Structured information accompanying the text such as user turn, user mentions, timestamps, is used as a cue by the participants themselves who need to follow the conversation and has been shown to be important for disentanglement. DAG-LSTMs, a generalization of Tree-LSTMs that can handle directed acyclic dependencies, are a natural way to incorporate such information and its non-sequential nature. In this paper, we apply DAG-LSTMs to the conversation disentanglement task. We perform our experiments on the Ubuntu IRC dataset. We show that the novel model we propose achieves state of the art status on the task of recovering reply-to relations and it is competitive on other disentanglement metrics.

Related papers

• Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models [0.0]
  We introduce a dynamic benchmarking system for conversational agents that evaluates their performance through a single, simulated, and lengthy user interaction. We context switch regularly to interleave the tasks, which constructs a realistic testing scenario in which we assess the Long-Term Memory, Continual Learning, and Information Integration capabilities of the agents.
  arXiv  Detail & Related papers  (2024-09-30T12:01:29Z)
• Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations [11.566214724241798]
  We propose a methodological pipeline to investigate model performance across specific structural attributes of conversations. We focus on Response Selection and Addressee Recognition tasks, to diagnose model weaknesses. Results show that response selection relies more on the textual content of conversations, while addressee recognition requires capturing their structural dimension.
  arXiv  Detail & Related papers  (2024-09-27T10:07:33Z)
• Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models [66.24055500785657]
  Traditional turn-based chat systems prevent users from verbally interacting with system while it is generating responses. To overcome these limitations, we adapt existing LLMs to listen users while generating output and provide users with instant feedback. We build a dataset consisting of alternating time slices of queries and responses as well as covering typical feedback types in instantaneous interactions.
  arXiv  Detail & Related papers  (2024-06-22T03:20:10Z)
• Thread of Thought Unraveling Chaotic Contexts [133.24935874034782]
  "Thread of Thought" (ThoT) strategy draws inspiration from human cognitive processes. In experiments, ThoT significantly improves reasoning performance compared to other prompting techniques.
  arXiv  Detail & Related papers  (2023-11-15T06:54:44Z)
• MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation [43.24092422054248]
  We propose a pipeline for refining instructions that enables large language models to effectively employ self-composed memos. We demonstrate a long-range open-domain conversation through iterative "memorization-retrieval-response" cycles. The instructions are reconstructed from a collection of public datasets to teach the LLMs to memorize and retrieve past dialogues with structured memos.
  arXiv  Detail & Related papers  (2023-08-16T09:15:18Z)
• End-to-end Spoken Conversational Question Answering: Task, Dataset and Model [92.18621726802726]
  In spoken question answering, the systems are designed to answer questions from contiguous text spans within the related speech transcripts. We propose a new Spoken Conversational Question Answering task (SCQA), aiming at enabling the systems to model complex dialogue flows. Our main objective is to build the system to deal with conversational questions based on the audio recordings, and to explore the plausibility of providing more cues from different modalities with systems in information gathering.
  arXiv  Detail & Related papers  (2022-04-29T17:56:59Z)
• Unsupervised Summarization for Chat Logs with Topic-Oriented Ranking and Context-Aware Auto-Encoders [59.038157066874255]
  We propose a novel framework called RankAE to perform chat summarization without employing manually labeled data. RankAE consists of a topic-oriented ranking strategy that selects topic utterances according to centrality and diversity simultaneously. A denoising auto-encoder is designed to generate succinct but context-informative summaries based on the selected utterances.
  arXiv  Detail & Related papers  (2020-12-14T07:31:17Z)
• Online Conversation Disentanglement with Pointer Networks [13.063606578730449]
  We propose an end-to-end online framework for conversation disentanglement. We design a novel way to embed the whole utterance that comprises timestamp, speaker, and message text. Our experiments on the Ubuntu IRC dataset show that our method achieves state-of-the-art performance in both link and conversation prediction tasks.
  arXiv  Detail & Related papers  (2020-10-21T15:43:07Z)
• Conversations with Search Engines: SERP-based Conversational Response Generation [77.1381159789032]
  We create a suitable dataset, the Search as a Conversation (SaaC) dataset, for the development of pipelines for conversations with search engines. We also develop a state-of-the-art pipeline for conversations with search engines, the Conversations with Search Engines (CaSE) using this dataset. CaSE enhances the state-of-the-art by introducing a supporting token identification module and aprior-aware pointer generator.
  arXiv  Detail & Related papers  (2020-04-29T13:07:53Z)
• Conversational Question Answering over Passages by Leveraging Word Proximity Networks [33.59664244897881]
  CROWN is an unsupervised yet effective system for conversational QA with passage responses. It supports several modes of context propagation over multiple turns. CROWN was evaluated on TREC CAsT data, where it achieved above-median performance in a pool of neural methods.
  arXiv  Detail & Related papers  (2020-04-27T19:30:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.