Information Bottleneck
Related Papers
Cross-dataset Clustering: Revealing Corresponding Themes across Multiple Corpora
We present a method for identifying corresponding themes across several corpora that are focused on related, but distinct, domains. This task is approached through simultaneous clustering of keyword sets extracted …...
Clustering Polysemic Subcategorization Frame Distributions Semantically
Previous research has demonstrated the utility of clustering in inducing semantic verb classes from undisambiguated cor- pus data. We describe a new approach which involves clustering subcategoriza- tion frame (SCF) …...
An Iterative Reinforcement Approach for Fine-Grained Opinion Mining
With the in-depth study of sentiment analysis research, finer-grained opinion mining, which aims to detect opinions on different review fea- tures as opposed to the whole review level, has been …...
BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle
AbstractThe principle of the Information Bottleneck (Tishby et al., 1999) produces a summary of information X optimized to predict some other relevant information Y. In this paper, we propose a …...
An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction
AbstractDecisions of complex models for language understanding can be explained by limiting the inputs they are provided to a relevant subsequence of the original text — a rationale. Models that …...
Graph Transformer Networks with Syntactic and Semantic Structures for Event Argument Extraction
AbstractThe goal of Event Argument Extraction (EAE) is to find the role of each entity mention for a given event trigger word. It has been shown in the previous works …...
DPR at SemEval-2021 Task 8: Dynamic Path Reasoning for Measurement Relation Extraction
AbstractScientific documents are replete with measurements mentioned in various formats and styles. As such, in a document with multiple quantities and measured entities, the task of associating each quantity to …...
Factorising Meaning and Form for Intent-Preserving Paraphrasing
AbstractWe propose a method for generating paraphrases of English questions that retain the original intent but use a different surface form. Our model combines a careful choice of training objective …...
Principled Paraphrase Generation with Parallel Corpora
AbstractRound-trip Machine Translation (MT) is a popular choice for paraphrase generation, which leverages readily available parallel corpora for supervision. In this paper, we formalize the implicit similarity function induced by …...
Referee: Reference-Free Sentence Summarization with Sharper Controllability through Symbolic Knowledge Distillation
AbstractWe present Referee, a novel framework for sentence summarization that can be trained reference-free (i.e., requiring no gold summaries for supervision), while allowing direct control for compression ratio. Our work …...
Span-based Named Entity Recognition by Generating and Compressing Information
AbstractThe information bottleneck (IB) principle has been proven effective in various NLP applications. The existing work, however, only used either generative or information compression models to improve the performance of …...