Жұмсақ назар
Related Papers
Bootstrapping Generators from Noisy Data
AbstractA core step in statistical data-to-text generation concerns learning correspondences between structured data representations (e.g., facts in a database) and associated texts. In this paper we aim to bootstrap generators …...
Zero-Shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens
AbstractCan attention- or gradient-based visualization techniques be used to infer token-level labels for binary sequence tagging problems, using networks trained only on sentence-level labels? We construct a neural network architecture …...
Exact Hard Monotonic Attention for Character-Level Transduction
AbstractMany common character-level, string-to-string transduction tasks, e.g., grapheme-to-phoneme conversion and morphological inflection, consist almost exclusively of monotonic transduction. Neural sequence-to-sequence models with soft attention, non-monotonic models, outperform popular monotonic models. …...
Look Harder: A Neural Machine Translation Model with Hard Attention
AbstractSoft-attention based Neural Machine Translation (NMT) models have achieved promising results on several translation tasks. These models attend all the words in the source sequence for each target token, which …...
Entity at SemEval-2021 Task 5: Weakly Supervised Token Labelling for Toxic Spans Detection
AbstractDetection of toxic spans - detecting toxicity of contents in the granularity of tokens - is crucial for effective moderation of online discussions. The baseline approach for this problem using …...
Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Information
AbstractVision language navigation is the task that requires an agent to navigate through a 3D environment based on natural language instructions. One key challenge in this task is to ground …...