HCTI at SemEval-2017 Task 1: Use convolutional neural network to
            evaluate Semantic Textual Similarity

Shao, Yang

doi:10.18653/v1/s17-2016

Cited by 51 publications

(44 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We observed that no word embedding has strong results on all the tasks. Although trained on the paraphrase database and having the highest |V | avai , the SL999 embedding could not outperform the Glove embedding in SICK-R. HCTI (Shao, 2017), which is the current state-of-the-art in the group of neural representation models on STSB, also used the Glove embedding. However, the performance of HTCI in STSB (78.4) is lower than our model using the Glove embedding.…”

Section: Evaluation Of Exploiting Multiple Pre-trained Word Embeddingsmentioning

confidence: 99%

“…SICK-R SICK-E MRPC Ensemble models/Feature engineering DT TEAM (Maharjan et al, 2017) 79.2 ---ECNU (Tian et al, 2017) 81 ---BIT 80.9 ---TF-KLD (Ji and Eisenstein, 2013) ---80.41/85.96 Neural representation models with one embedding Multi-Perspective CNN (He et al, 2015) -86.86 -78.6/84.73 InferSent (Conneau et al, 2017) 75.8 88.4 86.1 76.2/83.1 GRAN (Wieting and Gimpel, 2017) 76.4 86 --Paragram-Phrase (Wieting et al, 2016b) 73.2 86.84 85.3 -HCTI (Shao, 2017) 78.4 ---Neural representation models with the five embeddings using sentence-sentence comparison ( We report the results of these methods in Table 2. Overall, our M-MaxLSTM-CNN shows competitive performances in these tasks.…”

Section: Stsbmentioning

confidence: 99%

See 1 more Smart Citation

Sentence modeling via multiple word embeddings and multi-level comparison for semantic textual similarity

Tien

Yamasaki

et al. 2019

Information Processing & Management

View full text Add to dashboard Cite

Different word embedding models capture different aspects of linguistic properties. This inspired us to propose a model (M-MaxLSTM-CNN) for employing multiple sets of word embeddings for evaluating sentence similarity/relation. Representing each word by multiple word embeddings, the MaxLSTM-CNN encoder generates a novel sentence embedding. We then learn the similarity/relation between our sentence embeddings via Multi-level comparison. Our method M-MaxLSTM-CNN consistently shows strong performances in several tasks (i.e., measure textual similarity, identify paraphrase, recognize textual entailment). According to the experimental results on STS Benchmark dataset and SICK dataset from Se-mEval, M-MaxLSTM-CNN outperforms the state-of-the-art methods for textual similarity tasks. Our model does not use hand-crafted features (e.g., alignment features, Ngram overlaps, dependency features) as well as does not require pretrained word embeddings to have the same dimension.

show abstract

Section: Evaluation Of Exploiting Multiple Pre-trained Word Embeddingsmentioning

confidence: 99%

Section: Stsbmentioning

confidence: 99%

Sentence modeling via multiple word embeddings and multi-level comparison for semantic textual similarity

Tien

Yamasaki

et al. 2019

Information Processing & Management

View full text Add to dashboard Cite

show abstract

“…The techniques used are diverse and the results obtained are encouraging. Some apply neural network algorithms such as attention mechanisms [17] or convolutional networks [30]. Others compute variables from more traditional semantic and syntactic analysis tools such as alignment measures to feed supervised learning models [24].…”

Section: Semantic Similaritymentioning

confidence: 99%

User-in-the-loop adaptive intent detection for instructable digital assistant

Lair

Delgrange²,

Mugisha³

et al. 2020

Proceedings of the 25th International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

People are becoming increasingly comfortable using Digital Assistants (DAs) to interact with services or connected objects. However, for non-programming users, the available possibilities for customizing their DA are limited and do not include the possibility of teaching the assistant new tasks. To make the most of the potential of DAs, users should be able to customize assistants by instructing them through Natural Language (NL). To provide such functionalities, NL interpretation in traditional assistants should be improved: (1) The intent identification system should be able to recognize new forms of known intents, and to acquire new intents as they are expressed by the user. ( 2) In order to be adaptive to novel intents, the Natural Language Understanding module should be sample efficient, and should not rely on a pretrained model. Rather, the system should continuously collect the training data as it learns new intents from the user. In this work, we propose AidMe (Adaptive Intent Detection in Multi-Domain Environments), a user-in-the-loop adaptive intent detection framework that allows the assistant to adapt to its user by learning his intents as their interaction progresses. AidMe builds its repertoire of intents and collects data to train a model of semantic similarity evaluation that can discriminate between the learned intents and autonomously discover new forms of known intents. AidMe addresses two major issues -intent learning and user adaptation -for instructable digital assistants. We demonstrate the capabilities of AidMe as a standalone system by comparing it with a one-shot learning system and a pretrained NLU module through simulations of interactions with a user. We also show how AidMe can smoothly integrate to an existing instructable digital assistant.

show abstract

“…Similar to Focus layer, DPAD is one of the options for prediction layer at which we decide the similarity score and has been widely used in the literature [12,31]. To predict the similarity between a pair of questions, first, we extract each question's thought vector using one of the sentence embedding methods.…”

Section: Dot Product and Absolute Distance (Dpad)mentioning

confidence: 99%

Deep Contextualized Pairwise Semantic Similarity for Arabic Language Questions

Al-Bataineh

Farhan

Mustafa

et al. 2019

2019 IEEE 31st International Conference on Tools With Artificial Intelligence (ICTAI)

View full text Add to dashboard Cite

Question semantic similarity is a challenging and active research problem that is very useful in many NLP applications, such as detecting duplicate questions in community question answering platforms such as Quora. Arabic is considered to be an under-resourced language, has many dialects, and rich in morphology. Combined together, these challenges make identifying semantically similar questions in Arabic even more difficult. In this paper, we introduce a novel approach to tackle this problem, and test it on two benchmarks; one for Modern Standard Arabic (MSA), and another for the 24 major Arabic dialects. We are able to show that our new system outperforms state-of-the-art approaches by achieving 93% F1-score on the MSA benchmark and 82% on the dialectical one. This is achieved by utilizing contextualized word representations (ELMo embeddings) trained on a text corpus containing MSA and dialectic sentences. This in combination with a pairwise fine-grained similarity layer, helps our question-to-question similarity model to generalize predictions on different dialects while being trained only on question-to-question MSA data.

show abstract

HCTI at SemEval-2017 Task 1: Use convolutional neural network to evaluate Semantic Textual Similarity

Cited by 51 publications

References 10 publications

Sentence modeling via multiple word embeddings and multi-level comparison for semantic textual similarity

Sentence modeling via multiple word embeddings and multi-level comparison for semantic textual similarity

User-in-the-loop adaptive intent detection for instructable digital assistant

Deep Contextualized Pairwise Semantic Similarity for Arabic Language Questions

Contact Info

Product

Resources

About