Papers by Vadim Sheinin

8 papers
Identifying Motion Entities in Natural Language and A Case Study for Named Entity Recognition (2020.coling-main)

Copied to clipboard

Challenge: Identifying motion entities in text is not only challenging but beneficial for a better natural language understanding.
Approach: They propose a Motion Entity Tagging model to identify entities in motion in a text using the Literal-Motion-in-Text dataset for training and evaluating the model.
Outcome: The proposed method improves the Named-Entity Recognition task by splitting clauses and phrases from complex and long motion sentences.
QUEST: A Natural Language Interface to Relational Databases (L18-1)

Copied to clipboard

Challenge: Current systems focus on simple queries but neglect nested queries . nesting is a problem in SQL, but there is no easy way to achieve it .
Approach: They propose a system which can handle nested logic queries without restrictions . they propose QUEST, which can cope with nesting queries without restriction .
Outcome: The proposed system outperforms a baseline system by 11% accuracy.
SQL-to-Text Generation with Graph-to-Sequence Model (D18-1)

Copied to clipboard

Challenge: Existing approaches to generate SQL-to-text using seq2seq models do not capture graph-structured information in SQL query.
Approach: They propose a graph-to-sequence model to encode global structure information into node embeddings.
Outcome: The proposed model outperforms the Seq2Seq and Tree2Sq baselines on the WikiSQL and Stackoverflow datasets.
Addressing Limitations of Encoder-Decoder Based Approach to Text-to-SQL (2022.coling-1)

Copied to clipboard

Challenge: Existing attempts on Text-to-SQL task show a dramatic decline in performance for new databases.
Approach: They propose a hybrid system that integrates rule-based and deep learning components to improve model accuracy.
Outcome: The proposed system achieves double-digit percentage improvement for non-Spider databases.
A Large Resource of Patterns for Verbal Paraphrases (L18-1)

Copied to clipboard

Challenge: Xu et al., 2015: paraphrases play an important role in natural language understanding . he says it is difficult to propose a paraphrasing relation for natural language processing systems .
Approach: They propose a resource of such paraphrases that can be used to identify hidden paraphrase pairs . they propose to use the resource to identify paraphrase relationships between two words .
Outcome: The proposed resource contains tens of thousands of such pairs and is available for academic purposes.
Tackling Temporal Questions in Natural Language Interface to Databases (2022.emnlp-industry)

Copied to clipboard

Challenge: Temporal aspect is one of the most challenging areas in Natural Language Interface to Databases (NLIDB).
Approach: They propose a dataset with accompanied databases supporting temporal questions in NLIDB.
Outcome: The proposed dataset helps two models learn and improve in temporal aspect.
LiMiT: The Literal Motion in Text Dataset (2020.findings-emnlp)

Copied to clipboard

Challenge: Motion recognition is one of the basic cognitive capabilities of many life forms, yet identifying motion of physical entities in natural language have not been explored extensively and empirically.
Approach: They propose to use a human-annotated dataset to identify motion of physical entities in natural language.
Outcome: The proposed dataset analyzes the scale and diversity of the dataset and provides a baseline model.
Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model (D18-1)

Copied to clipboard

Challenge: Existing neural semantic parsers extract word order features while neglecting other valuable syntactic information.
Approach: They propose to use syntactic graph to represent three types of syntaktic information . they then employ a graph-to-sequence model to encode the syntastic graph and decode a logical form .
Outcome: The proposed model is comparable to the state-of-the-art on Jobs640, ATIS, and Geo880.

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