Related papers: Topological Sort for Sentence Ordering

Topological Sort for Sentence Ordering

URL: http://arxiv.org/abs/2005.00432v1
Date: Fri, 1 May 2020 15:07:59 GMT
Title: Topological Sort for Sentence Ordering
Authors: Shrimai Prabhumoye, Ruslan Salakhutdinov, Alan W Black
Abstract summary: We propose a new framing of this task as a constraint solving problem and introduce a new technique to solve it. The results on both automatic and human metrics across four different datasets show that this new technique is better at capturing coherence in documents.
Score: 133.05105352571715
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Sentence ordering is the task of arranging the sentences of a given text in the correct order. Recent work using deep neural networks for this task has framed it as a sequence prediction problem. In this paper, we propose a new framing of this task as a constraint solving problem and introduce a new technique to solve it. Additionally, we propose a human evaluation for this task. The results on both automatic and human metrics across four different datasets show that this new technique is better at capturing coherence in documents.

Related papers

MISMATCH: Fine-grained Evaluation of Machine-generated Text with Mismatch Error Types [68.76742370525234]
We propose a new evaluation scheme to model human judgments in 7 NLP tasks, based on the fine-grained mismatches between a pair of texts. Inspired by the recent efforts in several NLP tasks for fine-grained evaluation, we introduce a set of 13 mismatch error types. We show that the mismatch errors between the sentence pairs on the held-out datasets from 7 NLP tasks align well with the human evaluation.
arXiv Detail & Related papers (2023-06-18T01:38:53Z)
Conjunct Resolution in the Face of Verbal Omissions [51.220650412095665]
We propose a conjunct resolution task that operates directly on the text and makes use of a split-and-rephrase paradigm in order to recover the missing elements in the coordination structure. We curate a large dataset, containing over 10K examples of naturally-occurring verbal omissions with crowd-sourced annotations. We train various neural baselines for this task, and show that while our best method obtains decent performance, it leaves ample space for improvement.
arXiv Detail & Related papers (2023-05-26T08:44:02Z)
Fine-Grained Visual Entailment [51.66881737644983]
We propose an extension of this task, where the goal is to predict the logical relationship of fine-grained knowledge elements within a piece of text to an image. Unlike prior work, our method is inherently explainable and makes logical predictions at different levels of granularity. We evaluate our method on a new dataset of manually annotated knowledge elements and show that our method achieves 68.18% accuracy at this challenging task.
arXiv Detail & Related papers (2022-03-29T16:09:38Z)
Reinforcement Learning Based Query Vertex Ordering Model for Subgraph Matching [58.39970828272366]
Subgraph matching algorithms enumerate all is embeddings of a query graph in a data graph G. matching order plays a critical role in time efficiency of these backtracking based subgraph matching algorithms. In this paper, for the first time we apply the Reinforcement Learning (RL) and Graph Neural Networks (GNNs) techniques to generate the high-quality matching order for subgraph matching algorithms.
arXiv Detail & Related papers (2022-01-25T00:10:03Z)
Evaluating NLP Systems On a Novel Cloze Task: Judging the Plausibility of Possible Fillers in Instructional Texts [2.3449131636069898]
Cloze task is a widely used task to evaluate an NLP system's language understanding ability. New task is proposed: predicting if a filler word in a cloze task is a good, neutral, or bad candidate.
arXiv Detail & Related papers (2021-12-03T12:02:52Z)
STaCK: Sentence Ordering with Temporal Commonsense Knowledge [34.64198104134244]
Sentence order prediction is the task of finding the correct order of sentences in a randomly ordered document. We introduce STaCK -- a framework based on graph neural networks and temporal commonsense knowledge. We report results on five different datasets, and empirically show that the proposed method is naturally suitable for order prediction.
arXiv Detail & Related papers (2021-09-06T05:29:48Z)
BERT4SO: Neural Sentence Ordering by Fine-tuning BERT [26.050527288844005]
Recent work frames it as a ranking problem and applies deep neural networks to it. We propose a new method, named BERT4SO, by fine-tuning BERT for sentence ordering.
arXiv Detail & Related papers (2021-03-25T03:32:32Z)
Neural Sentence Ordering Based on Constraint Graphs [32.14555157902546]
Sentence ordering aims at arranging a list of sentences in the correct order. We devise a new approach based on multi-granular orders between sentences. These orders form multiple constraint graphs, which are then encoded by Graph Isomorphism Networks and fused into sentence representations.
arXiv Detail & Related papers (2021-01-27T02:53:10Z)
Few-Shot Semantic Parsing for New Predicates [33.84280840107834]
State-of-the-art neural semantics achieve less than 25% accuracy on benchmark datasets when k= 1. Our method consistently outperforms all the baselines in both one and two-shot settings.
arXiv Detail & Related papers (2021-01-26T11:08:08Z)
Incomplete Utterance Rewriting as Semantic Segmentation [57.13577518412252]
We present a novel and extensive approach, which formulates it as a semantic segmentation task. Instead of generating from scratch, such a formulation introduces edit operations and shapes the problem as prediction of a word-level edit matrix. Our approach is four times faster than the standard approach in inference.
arXiv Detail & Related papers (2020-09-28T09:29:49Z)

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