scholarly journals Combining Axiom Injection and Knowledge Base Completion for Efficient Natural Language Inference

2019 ◽  
Vol 33 ◽  
pp. 7410-7417 ◽  
Author(s):  
Masashi Yoshikawa ◽  
Koji Mineshima ◽  
Hiroshi Noji ◽  
Daisuke Bekki
Keyword(s):  
Natural Language ◽  
Knowledge Base ◽  
Processing Speed ◽  
Processing Time ◽  
State Of The Art ◽  
Proof Automation ◽  
New Knowledge ◽  
Textual Entailment ◽  
Amount Of Knowledge ◽  
Recognizing Textual Entailment

In logic-based approaches to reasoning tasks such as Recognizing Textual Entailment (RTE), it is important for a system to have a large amount of knowledge data. However, there is a tradeoff between adding more knowledge data for improved RTE performance and maintaining an efficient RTE system, as such a big database is problematic in terms of the memory usage and computational complexity. In this work, we show the processing time of a state-of-the-art logic-based RTE system can be significantly reduced by replacing its search-based axiom injection (abduction) mechanism by that based on Knowledge Base Completion (KBC). We integrate this mechanism in a Coq plugin that provides a proof automation tactic for natural language inference. Additionally, we show empirically that adding new knowledge data contributes to better RTE performance while not harming the processing speed in this framework.

scholarly journals Inherent Disagreements in Human Textual Inferences

2019 ◽  
Vol 7 ◽  
pp. 677-694
Author(s):  
Ellie Pavlick ◽  
Tom Kwiatkowski
Keyword(s):  
Natural Language ◽  
State Of The Art ◽  
Current State ◽  
Textual Entailment ◽  
Recognizing Textual Entailment

We analyze human’s disagreements about the validity of natural language inferences. We show that, very often, disagreements are not dismissible as annotation “noise”, but rather persist as we collect more ratings and as we vary the amount of context provided to raters. We further show that the type of uncertainty captured by current state-of-the-art models for natural language inference is not reflective of the type of uncertainty present in human disagreements. We discuss implications of our results in relation to the recognizing textual entailment (RTE)/natural language inference (NLI) task. We argue for a refined evaluation objective that requires models to explicitly capture the full distribution of plausible human judgments.

SANTM: Efficient Self-attention-driven Network for Text Matching

2022 ◽  
Vol 22 (3) ◽  
pp. 1-21
Author(s):  
Prayag Tiwari ◽  
Amit Kumar Jaiswal ◽  
Sahil Garg ◽  
Ilsun You
Keyword(s):  
Natural Language ◽  
State Of The Art ◽  
The State ◽  
Attention Mechanism ◽  
Matching Problems ◽  
Attention Model ◽  
Extra Information ◽  
Textual Entailment ◽  
Benchmark Datasets ◽  
Text Matching

Self-attention mechanisms have recently been embraced for a broad range of text-matching applications. Self-attention model takes only one sentence as an input with no extra information, i.e., one can utilize the final hidden state or pooling. However, text-matching problems can be interpreted either in symmetrical or asymmetrical scopes. For instance, paraphrase detection is an asymmetrical task, while textual entailment classification and question-answer matching are considered asymmetrical tasks. In this article, we leverage attractive properties of self-attention mechanism and proposes an attention-based network that incorporates three key components for inter-sequence attention: global pointwise features, preceding attentive features, and contextual features while updating the rest of the components. Our model follows evaluation on two benchmark datasets cover tasks of textual entailment and question-answer matching. The proposed efficient Self-attention-driven Network for Text Matching outperforms the state of the art on the Stanford Natural Language Inference and WikiQA datasets with much fewer parameters.

scholarly journals Deep Cascade Multi-Task Learning for Slot Filling in Online Shopping Assistant

2019 ◽  
Vol 33 ◽  
pp. 6465-6472 ◽  
Author(s):  
Yu Gong ◽  
Xusheng Luo ◽  
Yu Zhu ◽  
Wenwu Ou ◽  
Zhao Li ◽  
...  
Keyword(s):  
Natural Language ◽  
Knowledge Base ◽  
Online Shopping ◽  
State Of The Art ◽  
Language Understanding ◽  
Dialog Systems ◽  
Named Entity ◽  
Online Test ◽  
Benchmark Datasets ◽  
Slot Filling

Slot filling is a critical task in natural language understanding (NLU) for dialog systems. State-of-the-art approaches treat it as a sequence labeling problem and adopt such models as BiLSTM-CRF. While these models work relatively well on standard benchmark datasets, they face challenges in the context of E-commerce where the slot labels are more informative and carry richer expressions. In this work, inspired by the unique structure of E-commerce knowledge base, we propose a novel multi-task model with cascade and residual connections, which jointly learns segment tagging, named entity tagging and slot filling. Experiments show the effectiveness of the proposed cascade and residual structures. Our model has a 14.6% advantage in F1 score over the strong baseline methods on a new Chinese E-commerce shopping assistant dataset, while achieving competitive accuracies on a standard dataset. Furthermore, online test deployed on such dominant E-commerce platform shows 130% improvement on accuracy of understanding user utterances. Our model has already gone into production in the E-commerce platform.

Textual entailment graphs

2015 ◽  
Vol 21 (5) ◽  
pp. 699-724 ◽  
Author(s):  
LILI KOTLERMAN ◽  
IDO DAGAN ◽  
BERNARDO MAGNINI ◽  
LUISA BENTIVOGLI
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Gold Standard ◽  
State Of The Art ◽  
Text Analytics ◽  
Joint Work ◽  
Gold Standard Dataset ◽  
Textual Entailment ◽  
Interesting Task

AbstractIn this work, we present a novel type of graphs for natural language processing (NLP), namely textual entailment graphs (TEGs). We describe the complete methodology we developed for the construction of such graphs and provide some baselines for this task by evaluating relevant state-of-the-art technology. We situate our research in the context of text exploration, since it was motivated by joint work with industrial partners in the text analytics area. Accordingly, we present our motivating scenario and the first gold-standard dataset of TEGs. However, while our own motivation and the dataset focus on the text exploration setting, we suggest that TEGs can have different usages and suggest that automatic creation of such graphs is an interesting task for the community.

scholarly journals Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment

2020 ◽  
Vol 34 (05) ◽  
pp. 8018-8025 ◽  
Author(s):  
Di Jin ◽  
Zhijing Jin ◽  
Joey Tianyi Zhou ◽  
Peter Szolovits
Keyword(s):  
Machine Learning ◽  
Natural Language ◽  
Text Classification ◽  
Recurrent Neural Networks ◽  
State Of The Art ◽  
Semantic Content ◽  
Machine Learning Algorithms ◽  
Textual Entailment ◽  
Text Length ◽  
Adversarial Examples

Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models. It is helpful to evaluate or even improve the robustness of these models by exposing the maliciously crafted adversarial examples. In this paper, we present TextFooler, a simple but strong baseline to generate adversarial text. By applying it to two fundamental natural language tasks, text classification and textual entailment, we successfully attacked three target models, including the powerful pre-trained BERT, and the widely used convolutional and recurrent neural networks. We demonstrate three advantages of this framework: (1) effective—it outperforms previous attacks by success rate and perturbation rate, (2) utility-preserving—it preserves semantic content, grammaticality, and correct types classified by humans, and (3) efficient—it generates adversarial text with computational complexity linear to the text length.1

scholarly journals Recognizing textual entailment: Rational, evaluation and approaches – Erratum

2010 ◽  
Vol 16 (1) ◽  
pp. 105-105 ◽  
Author(s):  
IDO DAGAN ◽  
BILL DOLAN ◽  
BERNARDO MAGNINI ◽  
DAN ROTH
Keyword(s):  
Natural Language ◽  
Language Engineering ◽  
Textual Entailment ◽  
Recognizing Textual Entailment ◽  
Rational Evaluation

Due to publisher error, this article was omitted from the printed issue of Natural Language Engineering volume 15 issue 4.It is published online in the correct volume (journals.cambridge.org/nle) and also printed here in volume 16 issue 1. Sincere apologies are extended to the authors for this error.

scholarly journals Knowledge-Based Textual Inference via Parse-Tree Transformations

2015 ◽  
Vol 54 ◽  
pp. 1-57 ◽  
Author(s):  
Roy Bar-Haim ◽  
Ido Dagan ◽  
Jonathan Berant
Keyword(s):  
Natural Language ◽  
Relation Extraction ◽  
Practical Applications ◽  
Knowledge Based ◽  
Tree Transformations ◽  
Textual Entailment ◽  
Automatic Methods ◽  
Parse Trees ◽  
Recognizing Textual Entailment ◽  
Meaning Representation

Textual inference is an important component in many applications for understanding natural language. Classical approaches to textual inference rely on logical representations for meaning, which may be regarded as "external" to the natural language itself. However, practical applications usually adopt shallower lexical or lexical-syntactic representations, which correspond closely to language structure. In many cases, such approaches lack a principled meaning representation and inference framework. We describe an inference formalism that operates directly on language-based structures, particularly syntactic parse trees. New trees are generated by applying inference rules, which provide a unified representation for varying types of inferences. We use manual and automatic methods to generate these rules, which cover generic linguistic structures as well as specific lexical-based inferences. We also present a novel packed data-structure and a corresponding inference algorithm that allows efficient implementation of this formalism. We proved the correctness of the new algorithm and established its efficiency analytically and empirically. The utility of our approach was illustrated on two tasks: unsupervised relation extraction from a large corpus, and the Recognizing Textual Entailment (RTE) benchmarks.

scholarly journals Ordinal Common-sense Inference

2017 ◽  
Vol 5 ◽  
pp. 379-395 ◽  
Author(s):  
Sheng Zhang ◽  
Rachel Rudinger ◽  
Kevin Duh ◽  
Benjamin Van Durme
Keyword(s):  
Natural Language ◽  
Common Sense ◽  
Textual Entailment ◽  
Recognizing Textual Entailment ◽  
Common Sense Knowledge

Humans have the capacity to draw common-sense inferences from natural language: various things that are likely but not certain to hold based on established discourse, and are rarely stated explicitly. We propose an evaluation of automated common-sense inference based on an extension of recognizing textual entailment: predicting ordinal human responses on the subjective likelihood of an inference holding in a given context. We describe a framework for extracting common-sense knowledge from corpora, which is then used to construct a dataset for this ordinal entailment task. We train a neural sequence-to-sequence model on this dataset, which we use to score and generate possible inferences. Further, we annotate subsets of previously established datasets via our ordinal annotation protocol in order to then analyze the distinctions between these and what we have constructed.

Recognizing textual entailment: Rational, evaluation and approaches

2009 ◽  
Vol 15 (4) ◽  
pp. i-xvii ◽  
Author(s):  
IDO DAGAN ◽  
BILL DOLAN ◽  
BERNARDO MAGNINI ◽  
DAN ROTH
Keyword(s):  
Natural Language ◽  
Question Answering ◽  
Natural Language Understanding ◽  
Language Understanding ◽  
Knowledge Representations ◽  
Semantic Relationships ◽  
Textual Entailment ◽  
Inference Methods ◽  
Recognizing Textual Entailment ◽  
Core Problem

AbstractThe goal of identifying textual entailment – whether one piece of text can be plausibly inferred from another – has emerged in recent years as a generic core problem in natural language understanding. Work in this area has been largely driven by the PASCAL Recognizing Textual Entailment (RTE) challenges, which are a series of annual competitive meetings. The current work exhibits strong ties to some earlier lines of research, particularly automatic acquisition of paraphrases and lexical semantic relationships and unsupervised inference in applications such as question answering, information extraction and summarization. It has also opened the way to newer lines of research on more involved inference methods, on knowledge representations needed to support this natural language understanding challenge and on the use of learning methods in this context. RTE has fostered an active and growing community of researchers focused on the problem of applied entailment. This special issue of the JNLE provides an opportunity to showcase some of the most important work in this emerging area.

Sign in / Sign up

Export Citation Format

Share Document