Neural model parses non-projective dependency trees efficiently.
problem Parsing non-projective dependency trees.
method Probabilistic parsing model using neural representations and Kirchhoff's Matrix-Tree Theorem.
result State-of-the-art parsing performance on nine datasets.
Graph-to-Tree Neural Networks improve structured input-output translation in tasks like semantic parsing and math word problems.
problem Improving performance on tasks like semantic parsing and math word problem solving.
method Graph-to-Tree Neural Networks, consisting of a graph encoder and a hierarchical tree decoder.
result Graph2Tree model outperforms or matches state-of-the-art models on neural semantic parsing and math word problem tasks.
Neural parser learns to decompose objects into segments without ground truth.
problem Learning to decompose spatial tasks into segments for robots.
method Formulated as parsing approach, learned to imitate expert using DRAG policy gradient.
result Neural parser generalizes to natural images without ground truth.
Improves semantic parsing with human feedback in a counterfactual setup.
problem Expensive gold parses or answers for training semantic parsers.
method Convert model outputs to human-understandable statements for feedback.
result Significant improvement in semantic parsing through counterfactual learning.
Improves neural semantic parsers using human feedback.
problem Improving neural semantic parsers through human feedback.
method Counterfactual learning from human bandit feedback, reweighting estimator, stochastic gradient optimization.
result Significant improvement in semantic parsers achieved.
PATOIS synthesizes code from natural language using learned code idioms.
problem Synthesizing general-purpose source code from natural language specifications is challenging.
method PATOIS uses a neural synthesizer that interleaves high-level and low-level reasoning, incorporating learned code idioms from a corpus.
result Using learned code idioms improves the synthesizer's accuracy on semantic parsing datasets.
Synthetic reference strings are as effective as real ones for training citation parsing models.
problem Lack of training data for citation parsing, especially with deep neural networks.
method Trained Grobid with human-labelled and synthetically created reference strings, and evaluated retraining and out-of-sample data impact.
result Synthetic and real reference strings are equally effective for training Grobid, with retraining improving performance.
Automatically mined rules from dependency parsing help neural models learn from less labeled data.
problem Lack of labeled data for aspect and opinion term extraction.
method Automatically mined rules from dependency parsing, applied to auxiliary data, combined with human-annotated data.
result Neural models achieve better performance than state-of-the-art with mined rules and auxiliary data.
Novel ramp loss method improves weakly supervised machine translation and parsing.
problem Training neural models without gold labels in weak supervision scenarios.
method Adapted ramp loss objectives to promote positive outputs and discourage negative ones.
result Bipolar ramp loss objectives outperform other methods on weakly supervised tasks.
Paper proposes zero-shot transfer learning for semantic parsing.
problem Applying neural networks to tasks with little data remains challenging.
method Introduces a new method for learning shared space between domains based on domain label prediction.
result Method outperforms state-of-the-art techniques in zero-shot experimental setting.
Privacy-preserving syntactic parsing using obfuscation.
problem Preserving privacy while parsing encrypted natural language data.
method Introducing a neural model that obfuscates words in natural language texts, preserving syntactic relationships.
result The obfuscated text leads to better performance on syntactic parsers compared to a random substitution baseline.
A method for non-projective dependency parsing without fixed edge order.
problem Non-projective dependency parsing without fixed edge order.
method Incremental edge prediction, blending graph, transition, and easy-first parsing.
result Successfully parses near state-of-the-art on projective and non-projective languages.
Expanding spoken language understanding to handle complex entities and intents.
problem Handling compound entities and intents in spoken language understanding.
method Introducing a domain-agnostic shallow parser that handles linguistic coordination, learning domain-independent and slot-independent features.
result The model learns to segment conjunct boundaries of various phrasal categories and improves generalization across different slot types using adversarial training.
Unsupervised RNNGs perform similarly to supervised ones in language modeling and grammar induction.
problem Training RNNGs requires annotated data, which is costly.
method Amortized variational inference with a neural CRF parser.
result Unsupervised RNNGs achieve comparable performance to supervised ones.
This paper explores unsupervised learning of parsing models along two directions. First, which models are identifiable from infinite data? We use a general technique for numerically checking identifiability based on the rank of a Jacobian matrix, and apply it to several standard constituency and dependency parsing mode…
Neurally-Guided Structure Inference combines search and data-driven methods for efficient, robust structure inference.
problem Combining the advantages of exhaustive search and data-driven methods for structure inference.
method Neurally-Guided Structure Inference (NG-SI) uses a neural network to guide hierarchical search over structures.
result NG-SI outperforms search-based and data-driven methods on probabilistic matrix decomposition and symbolic program parsing.
Scene parsing is an important and challenging prob- lem in computer vision. It requires labeling each pixel in an image with the category it belongs to. Tradition- ally, it has been approached with hand-engineered features from color information in images. Recently convolutional neural networks (CNNs), which automatica…
Paper proposes a reinforcement learning framework for distant supervision of question parsing.
problem Lack of gold annotations for parsing in QA datasets.
method Reinforcement learning framework based on formal queries to learn mentions of entities and relations.
result Significant improvement in entity and relation linking compared to state of the art.
Flexible log file parsing using HMM adapts to evolving content.
problem Dynamic log file processing with evolving content.
method Modeling frequent patterns into HMM for flexible log file parsing.
result High accuracy (over 99%) in parsing different system log files.
Abstract Syntax Networks generate code and parse text with high accuracy.
problem Mapping unstructured inputs to well-formed outputs for code generation and semantic parsing.
method Dynamic AST construction using a decoder with a modular structure.
result 79.2 BLEU and 22.7% exact match accuracy on Hearthstone dataset.
DocParser parses document structures from renderings like PDFs and scans.
problem Parsing complete hierarchical document structures from renderings.
method End-to-end system with novel weak supervision approach.
result Significant improvement in document structure parsing performance.
Domain-general semantic parsing is a long-standing goal in natural language processing, where the semantic parser is capable of robustly parsing sentences from domains outside of which it was trained. Current approaches largely rely on additional supervision from new domains in order to generalize to those domains. We …
Deep models learn to parse complex language structures from local data patterns.
problem Understanding how deep models parse and represent language structures.
method Introduced tunable probabilistic context-free grammars and a learning algorithm inspired by deep networks.
result Data correlations across scales enable hierarchical language representations.
A new CNN-based code generator outperforms RNNs by 5%.
problem Capturing long sequences in code generation using RNNs.
method Grammar-based structural CNN with tree-based and pre-order convolution modules.
result Significantly outperforms previous state-of-the-art methods by 5 percentage points.
New meta-learning method outperforms human-designed architectures in dense image prediction tasks.
problem Designing efficient neural network architectures for dense image prediction.
method Recursive search space construction for multi-scale visual information.
result Meta-learning method achieves state-of-the-art performance on scene parsing, person-part segmentation, and semantic image segmentation.
MAPO uses a memory buffer to improve policy optimization in structured prediction tasks.
problem Improving sample efficiency and robustness in policy optimization for structured prediction tasks.
method Memory Augmented Policy Optimization (MAPO) uses a memory buffer to reduce policy gradient variance.
result MAPO achieves state-of-the-art results in program synthesis and semantic parsing tasks.
SparseMAP selects sparse structures efficiently for structured prediction.
problem Efficiently searching over combinatorial structures in structured prediction.
method SparseMAP: a new method for sparse structured inference with a differentiable loss function.
result SparseMAP selects only a few global structures efficiently.
Co-PLNet combines point and line predictions to improve wireframe parsing accuracy and efficiency.
problem Separate line and point predictions lead to inconsistent wireframes.
method Co-PLNet uses a Point-Line Prompt Encoder to convert early point detections into spatial prompts, which guide line refinement.
result Co-PLNet achieves better accuracy and robustness in wireframe parsing compared to existing methods.
Proposes a method to interpret linguistic data models using parse trees and least-squares scores.
problem Interpreting trained classification models in linguistic data sets.
method Assigns least-squares based importance scores to words in a sentence using syntactic constituency structure and relates them to the Banzhaf value in coalitional game theory.
result Demonstrates the effectiveness of the proposed method in aiding interpretability and diagnostics for language models.
Improved RNNs reduce memory decay and enhance language tasks.
problem Memory decay in RNNs affects performance in sequence prediction tasks.
method Introduced trainable scaling factors and a dependent bidirectional RNN to mitigate memory decay and improve performance.
result The proposed ELSTM and DBRNN models achieved up to 30% improvement in LAS compared to LSTM and GRU in dependency parsing.
We present the multiplicative recurrent neural network as a general model for compositional meaning in language, and evaluate it on the task of fine-grained sentiment analysis. We establish a connection to the previously investigated matrix-space models for compositionality, and show they are special cases of the multi…
Survey on automating geometry problem solving with large models.
problem Automating geometric problem solving with spatial understanding and logical reasoning.
method Synthesizes GPS advancements through benchmark construction, parsing, and reasoning paradigms.
result Unified analytical paradigm and emerging opportunities identified.
Unsupervised algorithm parses CSG images into CFG without pretraining.
problem Sparse reward problem in unsupervised program synthesis for images.
method Grammar-encoded tree LSTM, entropy regularization, sampling without replacement.
result Recover meaningful programs in large search spaces (up to 3.8imes1028). New method interprets complex models for music and urban simulations.
problem Difficulties in understanding deep neural network predictions.
method Uses generative models to improve explanation clarity.
result Flexibility demonstrated across diverse modalities (music, urban simulations).
Recently, deep architectures, such as recurrent and recursive neural networks have been successfully applied to various natural language processing tasks. Inspired by bidirectional recurrent neural networks which use representations that summarize the past and future around an instance, we propose a novel architecture …
AutoKE automates embedding physical knowledge into neural networks for complex engineering problems.
problem Complex physical equations in engineering problems.
method AutoKE framework using deep neural networks, equation parsing, automatic differentiation, adaptive weights, and NAS.
result Automatically embeds physical knowledge into neural networks for complex equations efficiently.
Combines RL and MML to learn programs from indirect supervision.
problem Learning programs from indirect supervision without spurious solutions.
method Connects RL and MML, uses systematic search and randomized exploration.
result Significant gains over state-of-the-art semantic parsers.
Capsule networks improve at detecting changes in compositionality with routing.
problem Capsule networks struggle with detecting changes in compositionality.
method Introduced a loss function based on routing entropy to improve compositionality.
result Capsule networks with the new loss function better detect changes in compositionality.
This work tackles extractive compression by formulating it as tree transduction.
problem Extractive compression as a challenging natural language processing problem.
method Formulated as a parse tree transduction problem, using a deep neural model with Long Short-Term Memory extended to consider parent-child relationships.
result Achieves state-of-the-art performance on sentence compression benchmarks.
Minimal domain knowledge used for malware detection with neural networks.
problem Malware detection without explicit feature construction.
method Restricting domain knowledge to extract PE header features and using neural networks.
result Neural networks can learn from raw bytes and perform better than explicit feature approaches.
NeSS combines neural and symbolic approaches for better compositional generalization.
problem Lack of compositional generalization in deep learning models.
method NeSS uses a neural network to generate traces, executed by a symbolic stack machine with sequence manipulation.
result Achieves 100% generalization performance across multiple domains.
Bayesian framework refines scene interpretation with prior and posterior models.
problem Challenges in incorporating contextual relationships into scene recognition.
method Combines prior scene geometry and object spatial arrangement with classifier outputs.
result Progressive refinement of scene interpretation through mutual information maximization.
Fast, format-agnostic web content detection for security.
problem Detecting malicious web content efficiently and accurately.
method Deep learning on static HTML tokens, avoiding complex parsing.
result 97.5% detection rate at 0.1% false positive rate.
Sequence to sequence learning has recently emerged as a new paradigm in supervised learning. To date, most of its applications focused on only one task and not much work explored this framework for multiple tasks. This paper examines three multi-task learning (MTL) settings for sequence to sequence models: (a) the onet…
Recurrent neural networks (RNNs) process input text sequentially and model the conditional transition between word tokens. In contrast, the advantages of recursive networks include that they explicitly model the compositionality and the recursive structure of natural language. However, the current recursive architectur…
Framework for universal graph function approximators outperforms existing methods.
problem Graph classification and separation of graph classes.
method Inspired by persistent homology, dependency parsing, and multivalued functions, the framework constructs universal approximators on graph isomorphism classes.
result Achieves state-of-the-art performance on four graph datasets.
Visualizes 3D CNNs for protein-ligand scoring.
problem Interpreting complex neural network decisions for protein-ligand scoring.
method Three visualization methods for 3D CNNs, including filters and weights.
result Visualizations aid in tuning and designing neural networks.
Program synthesis struggles with complex spatial relationships in image classification.
problem Challenges in solving Synthetic Visual Reasoning Test problems.
method Quantitative reanalysis of human and machine performance, improved program synthesis classifier, categorization of SVRT problems.
result Program synthesis is constrained by spatial relationships in images, not just shape specification.