Neural Semantic Encoders
We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the understanding of input sequences through read}, compose and write operations. NSE can also access multiple and shared memories. In this paper, we demonstrated the effectiveness and the flexibility of NSE on five different natural language tasks: natural language inference, question answering, sentence classification, document sentiment analysis and machine translation where NSE achieved state-of-the-art performance when evaluated on publically available benchmarks. For example, our shared-memory model showed an encouraging result on neural machine translation, improving an attention-based baseline by approximately 1.0 BLEU.
Code (3)
Tasks
General ClassificationMachine TranslationNatural Language InferenceNatural Language UnderstandingQuestion AnsweringSentenceSentence ClassificationSentiment AnalysisTranslationSimilar Papers 제목 키워드 기반
Crossing Variational Autoencoders for Answer Retrieval
Answer retrieval is to find the most aligned answer from a large set of candidates given a question. Learning vector representations of questions/answers is the key factor. Question-answer alignment and question/answer s…
RetrievalIntroducing Semantics into Speech Encoders
Recent studies find existing self-supervised speech encoders contain primarily acoustic rather than semantic information. As a result, pipelined supervised automatic speech recognition (ASR) to large language model (LLM)…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Entity Resolutionintent-classification+10The Daunting Dilemma with Sentence Encoders: Success on Standard Benchmarks, Failure in Capturing Basic Semantic Properties
In this paper, we adopted a retrospective approach to examine and compare five existing popular sentence encoders, i.e., Sentence-BERT, Universal Sentence Encoder (USE), LASER, InferSent, and Doc2vec, in terms of their p…
SentenceRFBNet: Deep Multimodal Networks with Residual Fusion Blocks for RGB-D Semantic Segmentation
RGB-D semantic segmentation methods conventionally use two independent encoders to extract features from the RGB and depth data. However, there lacks an effective fusion mechanism to bridge the encoders, for the purpose …
Semantic SegmentationDirect Network Transfer: Transfer Learning of Sentence Embeddings for Semantic Similarity
Sentence encoders, which produce sentence embeddings using neural networks, are typically evaluated by how well they transfer to downstream tasks. This includes semantic similarity, an important task in natural language …
Natural Language UnderstandingSemantic SimilaritySemantic Textual SimilaritySentence+3