1. The input embedding layer.
2. The context encoding layer.
3. The interaction and attention layer.
4. The output classification layer.

University of Michigan - Ann Arbor

It's a fundamental paradigm of NLP downstream. Basically, researchers are asked to model sentence pairs' relationship, including similarity, inference, comprehension, question answering and other complex semantic relationships.

Sentence Pair Modelling

Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering

It  identifies whether two sentences express the same meaning.

Paraphrase Identification (PI)

The task requires sentence matching between a passage and a question, pointing out the text region that contains the answer.

Machine Comprehension (MC)

Natural Language Inference (NLI), also known as text entailment, is a text-pair task that determines whether a given hypothesis can be logically inferred or entailed from a premise text. This requires the model to understand the semantic relationship between the two texts.

Natural Language Inference

Question Answering is a computer science discipline within the fields of information retrieval and natural language processing (NLP), which is concerned with building systems that automatically answer questions posed by humans in a natural language.

Question Answering

Components of General Framework for Sentence Pair Modelling

1. Sentence Bert
2. Mirror-Bert/ SimCSE
3. Augmented SBert
4. TransEncoder

Representative Papers of Sentence Pair Modeling

Bi-Encoder and Cross-Encoder

1. (BERT Paradigm) Sentence pair segmented by [SEP].
2. Attention-based structure. e.g ABCNN, other soft-alignment mechanism
3. Siamse Network.
4. Multi-perspective matching.

Representative Models of Sentence Pair Modeling

1. SNLI
2. Multi-NLI
3. Quora
4. Twitter-URL
5. PIT-2015
6. STS-2014
7. WikiQA
8. TrecQA

Sentence Pair Related Datasets

Sentence Textual Similarity (STS) is a task that measures the degree of semantic equivalence between two pieces of text. It is also referred to as semantic equivalence judgement, where the goal is to determine if two texts convey the same meaning.

Learn Before

Related