scholarly journals Co-Attention Hierarchical Network: Generating Coherent Long Distractors for Reading Comprehension

2020 ◽  
Vol 34 (05) ◽  
pp. 9725-9732
Author(s):  
Xiaorui Zhou ◽  
Senlin Luo ◽  
Yunfang Wu
Keyword(s):  
Reading Comprehension ◽  
Semantic Similarity ◽  
State Of The Art ◽  
Deep Understanding ◽  
Hierarchical Architecture ◽  
Hierarchical Network ◽  
Word Level ◽  
Human Evaluation ◽  
Sentence Level ◽  
The Relationship

In reading comprehension, generating sentence-level distractors is a significant task, which requires a deep understanding of the article and question. The traditional entity-centered methods can only generate word-level or phrase-level distractors. Although recently proposed neural-based methods like sequence-to-sequence (Seq2Seq) model show great potential in generating creative text, the previous neural methods for distractor generation ignore two important aspects. First, they didn't model the interactions between the article and question, making the generated distractors tend to be too general or not relevant to question context. Second, they didn't emphasize the relationship between the distractor and article, making the generated distractors not semantically relevant to the article and thus fail to form a set of meaningful options. To solve the first problem, we propose a co-attention enhanced hierarchical architecture to better capture the interactions between the article and question, thus guide the decoder to generate more coherent distractors. To alleviate the second problem, we add an additional semantic similarity loss to push the generated distractors more relevant to the article. Experimental results show that our model outperforms several strong baselines on automatic metrics, achieving state-of-the-art performance. Further human evaluation indicates that our generated distractors are more coherent and more educative compared with those distractors generated by baselines.

scholarly journals Generating Distractors for Reading Comprehension Questions from Real Examinations

2019 ◽  
Vol 33 ◽  
pp. 6423-6430 ◽  
Author(s):  
Yifan Gao ◽  
Lidong Bing ◽  
Piji Li ◽  
Irwin King ◽  
Michael R. Lyu
Keyword(s):  
Reading Comprehension ◽  
Multiple Choice ◽  
Semantic Context ◽  
Time Step ◽  
Word Level ◽  
Human Evaluation ◽  
Sentence Level ◽  
Dynamic Attention

We investigate the task of distractor generation for multiple choice reading comprehension questions from examinations. In contrast to all previous works, we do not aim at preparing words or short phrases distractors, instead, we endeavor to generate longer and semantic-rich distractors which are closer to distractors in real reading comprehension from examinations. Taking a reading comprehension article, a pair of question and its correct option as input, our goal is to generate several distractors which are somehow related to the answer, consistent with the semantic context of the question and have some trace in the article. We propose a hierarchical encoderdecoder framework with static and dynamic attention mechanisms to tackle this task. Specifically, the dynamic attention can combine sentence-level and word-level attention varying at each recurrent time step to generate a more readable sequence. The static attention is to modulate the dynamic attention not to focus on question irrelevant sentences or sentences which contribute to the correct option. Our proposed framework outperforms several strong baselines on the first prepared distractor generation dataset of real reading comprehension questions. For human evaluation, compared with those distractors generated by baselines, our generated distractors are more functional to confuse the annotators.

scholarly journals DCMN+: Dual Co-Matching Network for Multi-Choice Reading Comprehension

2020 ◽  
Vol 34 (05) ◽  
pp. 9563-9570 ◽  
Author(s):  
Shuailiang Zhang ◽  
Hai Zhao ◽  
Yuwei Wu ◽  
Zhuosheng Zhang ◽  
Xi Zhou ◽  
...  
Keyword(s):  
Reading Comprehension ◽  
Reading Strategies ◽  
State Of The Art ◽  
Matching Network ◽  
Question And Answer ◽  
The Relationship ◽  
Answer Option ◽  
Comparison Information

Multi-choice reading comprehension is a challenging task to select an answer from a set of candidate options when given passage and question. Previous approaches usually only calculate question-aware passage representation and ignore passage-aware question representation when modeling the relationship between passage and question, which cannot effectively capture the relationship between passage and question. In this work, we propose dual co-matching network (DCMN) which models the relationship among passage, question and answer options bidirectionally. Besides, inspired by how humans solve multi-choice questions, we integrate two reading strategies into our model: (i) passage sentence selection that finds the most salient supporting sentences to answer the question, (ii) answer option interaction that encodes the comparison information between answer options. DCMN equipped with the two strategies (DCMN+) obtains state-of-the-art results on five multi-choice reading comprehension datasets from different domains: RACE, SemEval-2018 Task 11, ROCStories, COIN, MCTest.

scholarly journals Improving Semantic Similarity with Cross-Lingual Resources: A Study in Bangla—A Low Resourced Language

Informatics ◽  
2019 ◽  
Vol 6 (2) ◽  
pp. 19 ◽  
Author(s):  
Rajat Pandit ◽  
Saptarshi Sengupta ◽  
Sudip Kumar Naskar ◽  
Niladri Sekhar Dash ◽  
Mohini Mohan Sardar
Keyword(s):  
Semantic Similarity ◽  
Language Processing ◽  
State Of The Art ◽  
Human Beings ◽  
Human Evaluation ◽  
Evaluation Scores ◽  
Similarity Calculation ◽  
Marked Enhancement ◽  
Cross Lingual ◽  
Standing Problem

Semantic similarity is a long-standing problem in natural language processing (NLP). It is a topic of great interest as its understanding can provide a look into how human beings comprehend meaning and make associations between words. However, when this problem is looked at from the viewpoint of machine understanding, particularly for under resourced languages, it poses a different problem altogether. In this paper, semantic similarity is explored in Bangla, a less resourced language. For ameliorating the situation in such languages, the most rudimentary method (path-based) and the latest state-of-the-art method (Word2Vec) for semantic similarity calculation were augmented using cross-lingual resources in English and the results obtained are truly astonishing. In the presented paper, two semantic similarity approaches have been explored in Bangla, namely the path-based and distributional model and their cross-lingual counterparts were synthesized in light of the English WordNet and Corpora. The proposed methods were evaluated on a dataset comprising of 162 Bangla word pairs, which were annotated by five expert raters. The correlation scores obtained between the four metrics and human evaluation scores demonstrate a marked enhancement that the cross-lingual approach brings into the process of semantic similarity calculation for Bangla.

scholarly journals Assessing the relationship between Vocabulary Level Test (VLT) and reading comprehension

2017 ◽  
Vol 4 (2) ◽  
pp. 157
Author(s):  
Alpino Susanto
Keyword(s):  
Reading Comprehension ◽  
Undergraduate Students ◽  
Vocabulary Knowledge ◽  
Teaching Process ◽  
English Teaching ◽  
Word Level ◽  
Reading Activities ◽  
The Relationship

It has been considered crucial about how vocabulary knowledge in relation with reading comprehension. This research was conducted to explore the link of Indonesian students Vocabulary Level Test (VLT) performance and their reading textbook on reading subject. Through this pilot research, it can describe the implications profile in English teaching process especially in reading. Furthermore it can give more information in how to measure the reading textbook reference for reading subject or other similar subject that involve reading activities. There were 30 undergraduate students in Universitas Putera Batam that participated in the VLT. Their English textbook (Mosaic 1) was profiled to measure the lexical vocabulary level. The results indicated that only 1% of the participants had mastered the 2000-word level which means the vocabulary textbook-level is still far from students vocabulary knowledge. From the level of comparison theoretically they would have difficulties to comprehend the reading textbook, and some additional activities would be recommended, before, during and after the reading subject. 

scholarly journals Improving the state-of-the-art in Thai semantic similarity using distributional semantics and ontological information

PLoS ONE ◽  
2021 ◽  
Vol 16 (2) ◽  
pp. e0246751
Author(s):  
Ponrudee Netisopakul ◽  
Gerhard Wohlgenannt ◽  
Aleksei Pulich ◽  
Zar Zar Hlaing
Keyword(s):  
Semantic Similarity ◽  
Language Processing ◽  
English Language ◽  
State Of The Art ◽  
Word Sense Disambiguation ◽  
Similarity Score ◽  
The State ◽  
Word Sense ◽  
Word Level ◽  
High Fraction

Research into semantic similarity has a long history in lexical semantics, and it has applications in many natural language processing (NLP) tasks like word sense disambiguation or machine translation. The task of calculating semantic similarity is usually presented in the form of datasets which contain word pairs and a human-assigned similarity score. Algorithms are then evaluated by their ability to approximate the gold standard similarity scores. Many such datasets, with different characteristics, have been created for English language. Recently, four of those were transformed to Thai language versions, namely WordSim-353, SimLex-999, SemEval-2017-500, and R&G-65. Given those four datasets, in this work we aim to improve the previous baseline evaluations for Thai semantic similarity and solve challenges of unsegmented Asian languages (particularly the high fraction of out-of-vocabulary (OOV) dataset terms). To this end we apply and integrate different strategies to compute similarity, including traditional word-level embeddings, subword-unit embeddings, and ontological or hybrid sources like WordNet and ConceptNet. With our best model, which combines self-trained fastText subword embeddings with ConceptNet Numberbatch, we managed to raise the state-of-the-art, measured with the harmonic mean of Pearson on Spearman ρ, by a large margin from 0.356 to 0.688 for TH-WordSim-353, from 0.286 to 0.769 for TH-SemEval-500, from 0.397 to 0.717 for TH-SimLex-999, and from 0.505 to 0.901 for TWS-65.

scholarly journals The Relationship between Vocabulary Size and Reading Comprehension of ESL Learners

2016 ◽  
Vol 9 (2) ◽  
pp. 116 ◽  
Author(s):  
Engku Haliza Engku Ibrahim ◽  
Isarji Sarudin ◽  
Ainon Jariah Muhamad
Keyword(s):  
Reading Comprehension ◽  
English Language ◽  
Esl Students ◽  
Intensive English ◽  
Vocabulary Size ◽  
Word Level ◽  
Comprehension Skills ◽  
Admission Requirements ◽  
Esl Learners ◽  
The Relationship

<p>There are many factors that contribute to one’s ability to read effectively. Vocabulary size is one important factor that enhances reading comprehension. The purpose of the study is to examine the relationship between students’ reading comprehension skills and their vocabulary size. A total of 129 pre-university students undergoing an intensive English language programme at a public university in Malaysia participated in this study. A correlational analysis was employed to ascertain the relationship between scores in the reading comprehension component of the institutionalised English Proficiency Test (EPT) and the Vocabulary Levels Tests (Nation, 1990). Based on Pearson product moment correlation coefficient, there was a moderate correlation (r=0.641) between scores in the EPT reading comprehension and Vocabulary Levels Tests. The relationship was statistically significant at p&lt;0.01 level. The findings also indicate that all students (100%) were able to fulfil the minimum admission requirements for the reading skill (Band 5.5) in the EPT even though only half of the students (54.3%) reached the mastery level at the 5,000 word level. The findings provide useful insights into the prediction of ESL students’ performance in reading and the teaching of vocabulary in the ESL context.</p>

scholarly journals RTHN: A RNN-Transformer Hierarchical Network for Emotion Cause Extraction

2019 ◽  
Author(s):  
Rui Xia ◽  
Mengran Zhang ◽  
Zixiang Ding
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Relative Position ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Hierarchical Network ◽  
Classification Problems ◽  
Rule Based ◽  
Machine Learning Methods ◽  
Word Level

The emotion cause extraction (ECE) task aims at discovering the potential causes behind a certain emotion expression in a document. Techniques including rule-based methods, traditional machine learning methods and deep neural networks have been proposed to solve this task. However, most of the previous work considered ECE as a set of independent clause classification problems and ignored the relations between multiple clauses in a document. In this work, we propose a joint emotion cause extraction framework, named RNN-Transformer Hierarchical Network (RTHN), to encode and classify multiple clauses synchronously. RTHN is composed of a lower word-level encoder based on RNNs to encode multiple words in each clause, and an upper clause-level encoder based on Transformer to learn the correlation between multiple clauses in a document. We furthermore propose ways to encode the relative position and global predication information into Transformer that can capture the causality between clauses and make RTHN more efficient. We finally achieve the best performance among 12 compared systems and improve the F1 score of the state-of-the-art from 72.69% to 76.77%.

scholarly journals Learning semantic sentence representations from visually grounded language without lexical knowledge

2019 ◽  
Vol 25 (4) ◽  
pp. 451-466 ◽  
Author(s):  
Danny Merkx ◽  
Stefan L. Frank
Keyword(s):  
Visual Information ◽  
State Of The Art ◽  
Approaches To Learning ◽  
Semantic Content ◽  
Lexical Knowledge ◽  
Multimodal Data ◽  
Word Level ◽  
Current State ◽  
Sentence Level ◽  
Benchmark Datasets

AbstractCurrent approaches to learning semantic representations of sentences often use prior word-level knowledge. The current study aims to leverage visual information in order to capture sentence level semantics without the need for word embeddings. We use a multimodal sentence encoder trained on a corpus of images with matching text captions to produce visually grounded sentence embeddings. Deep Neural Networks are trained to map the two modalities to a common embedding space such that for an image the corresponding caption can be retrieved and vice versa. We show that our model achieves results comparable to the current state of the art on two popular image-caption retrieval benchmark datasets: Microsoft Common Objects in Context (MSCOCO) and Flickr8k. We evaluate the semantic content of the resulting sentence embeddings using the data from the Semantic Textual Similarity (STS) benchmark task and show that the multimodal embeddings correlate well with human semantic similarity judgements. The system achieves state-of-the-art results on several of these benchmarks, which shows that a system trained solely on multimodal data, without assuming any word representations, is able to capture sentence level semantics. Importantly, this result shows that we do not need prior knowledge of lexical level semantics in order to model sentence level semantics. These findings demonstrate the importance of visual information in semantics.

Automatic scoring of Chinese fill-in-the-blank questions based on improved P-means

2021 ◽  
pp. 1-10
Author(s):  
Wang Dong ◽  
Zhao Yong ◽  
Lin Hong ◽  
Zuo Xin
Keyword(s):  
Semantic Similarity ◽  
Test Site ◽  
Learning Ability ◽  
Common Word ◽  
Dictionary Matching ◽  
Word Test ◽  
Word Level ◽  
Subject Term ◽  
Sentence Level ◽  
Automatic Scoring

Chinese fill-in-the-blank questions contain both objective and subjective characteristics, and thus it has always been difficult to score them automatically. In this paper, fill-in-the-blank items are divided into those with word-level or sentence-level granularity; then, the items are automatically scored by different strategies. The automatic scoring framework combines semantic dictionary matching and semantic similarity calculations. First, fill-in-the-blank items with word-level granularity are divided into two types of test sites: the subject term test site, and the common word test site. We propose an algorithm for identifying an item’s test site. Then, a subject term dictionary with self-feedback learning ability is constructed to support the scoring of subject term test sites. The Tongyici Cilin semantic dictionary is used for scoring common word test sites. For fill-in-the-blank items with sentence-level granularity, an improved P-means model is used to generate a sentence vector of the standard answer and the examinee’s answer, and then the semantic similarity between the two answers is obtained by calculating the cosine distance of the sentence vector. Experimental results on actual test data show that the proposed algorithm has a maximum accuracy of 94.3% and achieves good results.

scholarly journals Aspect Sentiment Classification with both Word-level and Clause-level Attention Networks

2018 ◽  
Author(s):  
Jingjing Wang ◽  
Jie Li ◽  
Shoushan Li ◽  
Yangyang Kang ◽  
Min Zhang ◽  
...  
Keyword(s):  
Sentiment Analysis ◽  
Sentiment Classification ◽  
Experimental Results ◽  
Hierarchical Network ◽  
Attention Networks ◽  
Word Level ◽  
Sentence Level

Aspect sentiment classification, a challenging task in sentiment analysis, has been attracting more and more attention in recent years. In this paper, we highlight the need for incorporating the importance degrees of both words and clauses inside a sentence and propose a hierarchical network with both word-level and clause-level attentions to aspect sentiment classification. Specifically, we first adopt sentence-level discourse segmentation to segment a sentence into several clauses. Then, we leverage multiple Bi-directional LSTM layers to encode all clauses and propose a word-level attention layer to capture the importance degrees of words in each clause. Third and finally, we leverage another Bi-directional LSTM layer to encode the outputs from the former layers and propose a clause-level attention layer to capture the importance degrees of all the clauses inside a sentence. Experimental results on the laptop and restaurant datasets from SemEval-2015 demonstrate the effectiveness of our proposed approach to aspect sentiment classification.

Sign in / Sign up

Export Citation Format

Share Document