Challenge: a study of long documents that do not include short sections in their titles shows that they improve comprehension and speed .
Approach: They propose to extract the most salient sentence and apply deletion-based compression to generate section titles in low-resource environments.
Outcome: The proposed approach outperforms other methods in low-resource environments while outperforming other approaches.

Similar Papers

Filtered Semi-Markov CRF (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for sequence labeling tasks such as Named Entity Recognition (NER) suffer from quadratic complexity over sequence length and poor performance compared to CRF.
Approach: They propose a variant of Semi-Markov CRF that incorporates a filtering step to eliminate irrelevant segments, reducing complexity and search space.
Outcome: The proposed method outperforms both CRF and Semi-CRF on several NER benchmarks while being significantly faster.
STAPI: An Automatic Scraper for Extracting Iterative Title-Text Structure from Web Documents (2022.lrec-1)

Copied to clipboard

Challenge: Formal documents are organized into sections of text, each with a title . but there is no corpus of web documents annotated with titles and prose texts . cnn.com's john mccarthy and daniel mclears are working on a new title-text dataset .
Approach: They propose a first title-text dataset on web documents that incorporates a wide variety of domains to facilitate downstream training.
Outcome: The proposed system outperforms baseline models in terms of title-text identification.
Adversarial Domain Adaptation Using Artificial Titles for Abstractive Title Generation (P19-1)

Copied to clipboard

Challenge: Obtaining good quality labeled data can be difficult and expensive for abstractive summarization models . authors propose the use of artificial titles for unlabeled target documents .
Approach: They propose to use artificial titles and sequential training to capture grammatical style of unlabeled target domains to adapt to/from news articles and Stack Exchange posts.
Outcome: The proposed techniques can boost performance for unsupervised adaptation and fine-tuning with limited target data.
Multi-lingual neural title generation for e-Commerce browse pages (N18-3)

Copied to clipboard

Challenge: e-Commerce websites are automatically generating millions of browse pages . manual creation of titles is infeasible due to the huge number of browse page types .
Approach: They propose to use sequence-to-sequence models to generate titles for languages . they train the models on multi-lingual data, thereby creating one joint model .
Outcome: The proposed model can generate titles in three different languages, with a focus on low-resource French.
Title-based Extractive Summarization via MRC Framework (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies on extractive summarization focus on scoring and selecting summary sentences . existing models tend to select generalized sentences while overlooking the overall content of a document.
Approach: They propose a machine reading comprehension framework for extractive summarization by setting a query as the title.
Outcome: The proposed framework outperforms existing models on long and short summaries in Korean and English . it can consider the semantic coherence and relevance of summary sentences in relation to the overall content .
Supervised and Unsupervised Methods for Robust Separation of Section Titles and Prose Text in Web Documents (D18-1)

Copied to clipboard

Challenge: a web text structure is underutilized, but its visual organization is useful for NLP tasks . a flexible system for extracting hierarchical section titles and prose organization is developed .
Approach: a new system extracts hierarchical section titles and prose organization from web documents . the system uses features from syntax, semantics, discourse and markup to build two models .
Outcome: a new system extracts the hierarchical section titles and prose organization of web documents . the system achieves an overall precision of 0.82 and a recall of 0.98 on three domains of web text .
A Neural CRF-based Hierarchical Approach for Linear Text Segmentation (2023.findings-eacl)

Copied to clipboard

Challenge: Existing methods to segment unformatted text and transcripts explicitly train to predict segment boundaries, but they fail to provide a large annotated dataset.
Approach: They propose a method to generate hierarchical segmentation structures based on Wikipedia annotations by using a neural conditional random field.
Outcome: The proposed method outperforms or achieves competitive performance when compared to previous state-of-the-art algorithms.
Neural semi-Markov CRF for Monolingual Word Alignment (2021.acl-long)

Copied to clipboard

Challenge: Experimental results show that our proposed model outperforms all previous approaches for monolingual word alignment.
Approach: They propose a neural semi-Markov CRF alignment model which unifies word and phrase alignments through variable-length spans.
Outcome: The proposed model outperforms existing models on in-domain and out-of-domain evaluations and a QA-based benchmark with human annotations.
Towards Improving Neural Named Entity Recognition with Gazetteers (P19-1)

Copied to clipboard

Challenge: Currently, neural models for named entity recognition are based on data-driven models, with a strong emphasis on getting rid of the efforts for collecting external resources or designing hand-crafted features.
Approach: They propose to use external gazetteers to efficiently access annotated data to generalize beyond the annotation of entities.
Outcome: The proposed model can access external gazetteers while avoiding the effort to design hand-crafted features.
Re3val: Reinforced and Reranked Generative Retrieval (2024.findings-eacl)

Copied to clipboard

Challenge: generative retrieval models encode pointers to information in a corpus as an index within the model’s parameters.
Approach: They propose a generative retrieval model that leverages contextual information to rerank retrieved page titles and utilizes REINFORCE to maximize rewards generated by constrained decoding.
Outcome: The proposed model can't be tuned for the downstream readers as decoding the page title is a non-differentiable operation.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations