A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations
This work addresses a bottleneck in sentence matching for NLP applications, but it is incremental as it builds on existing deep models by enhancing local information capture.
The paper tackled the problem of capturing contextualized local information in sentence matching for applications like information retrieval and question answering, by introducing a deep architecture with multiple positional sentence representations using Bi-LSTM and k-Max pooling, and demonstrated its superiority in experiments on tasks such as question answering and sentence completion.
Matching natural language sentences is central for many applications such as information retrieval and question answering. Existing deep models rely on a single sentence representation or multiple granularity representations for matching. However, such methods cannot well capture the contextualized local information in the matching process. To tackle this problem, we present a new deep architecture to match two sentences with multiple positional sentence representations. Specifically, each positional sentence representation is a sentence representation at this position, generated by a bidirectional long short term memory (Bi-LSTM). The matching score is finally produced by aggregating interactions between these different positional sentence representations, through $k$-Max pooling and a multi-layer perceptron. Our model has several advantages: (1) By using Bi-LSTM, rich context of the whole sentence is leveraged to capture the contextualized local information in each positional sentence representation; (2) By matching with multiple positional sentence representations, it is flexible to aggregate different important contextualized local information in a sentence to support the matching; (3) Experiments on different tasks such as question answering and sentence completion demonstrate the superiority of our model.