Papers by Daniel Gildea
Leveraging Dependency Forest for Neural Medical Relation Extraction (D19-1)
Copied to clipboard
| Challenge: | Existing methods for medical relation extraction use dependency syntax as a source of features. |
| Approach: | They propose a method to extract relational information from medical literature by using dependency forests. |
| Outcome: | The proposed method outperforms the standard tree-based methods in the medical domain. |
Sequence-to-sequence AMR Parsing with Ancestor Information (2022.acl-short)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) is a graph that encodes the semantic meaning of a sentence. |
| Approach: | They propose several strategies to add important ancestor information into a Transformer Decoder. |
| Outcome: | The proposed methods improve performance for both AMR 2.0 and AMR 3.0 datasets and achieve new state-of-the-art results. |
Outside Computation with Superior Functions (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing generalized inside-outside algorithm would violate Strong Exponential Time Hypothesis (SETH) |
| Approach: | They propose a framework for efficient outside computation that would yield a sub-exponential time algorithm for SAT, violating the Strong Exponential Time Hypothesis (SETH). |
| Outcome: | The proposed algorithm would violate the Strong Exponential Time Hypothesis (SETH) . |
Sequence-to-sequence Models for Cache Transition Systems (P18-1)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) is a semantic formalism where the meaning of a sentence is encoded as a rooted, directed graph. |
| Approach: | They propose a sequence-to-sequence based approach for mapping natural language sentences to AMR semantic graphs using a special transition system called a cache transition system. |
| Outcome: | The proposed model outperforms other sequence-to-sequence approaches and achieves competitive results in comparison with the best-performing models. |
SemBleu: A Robust Metric for AMR Parsing Evaluation (P19-1)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) is a semantic formalism where the meaning of a sentence is encoded as a rooted, directed graph. |
| Approach: | They propose a metric that extends SMATCH to parse AMRs and does not suffer from search errors. |
| Outcome: | The proposed metric does not suffer from search errors and considers non-local correspondences in addition to local ones. |
A Graph-to-Sequence Model for AMR-to-Text Generation (P18-1)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) is a semantic formalism that encodes the meaning of a sentence as a rooted, directed graph. |
| Approach: | They propose a neural graph-to-sequence model that leverages LSTM to encode a linearized AMR structure. |
| Outcome: | The proposed model outperforms existing methods on a benchmark. |
Orthographic Features for Bilingual Lexicon Induction (P18-2)
Copied to clipboard
| Challenge: | Recent embedding-based methods do not take advantage of orthographic features, such as edit distance, which can be helpful for pairs of related languages. |
| Approach: | They propose to use orthographic features to integrate orthographic induction into embedding methods . they use document-aligned data instead of a seed dictionary to learn bilingual embedds . |
| Outcome: | This work extends embedding-based methods to incorporate orthographic features . it shows that the methods can learn bilingual embeddables in low-resource languages . |
Rewarding Semantic Similarity under Optimized Alignments for AMR-to-Text Generation (2022.acl-short)
Copied to clipboard
| Challenge: | Automatic evaluation metrics score natural language generation systems based on how well they lexically align to humanannotated references. |
| Approach: | They propose to replace greedy alignments in BERTScore with optimized ones that replace the n-gram matching BERTAcore metrics with a token embedding to prevent domain mismatch. |
| Outcome: | The proposed metrics outperform cross-entropy and BLEU reward baselines on AMR-to-text generation. |
Leveraging Context Information for Natural Question Generation (N18-2)
Copied to clipboard
| Challenge: | Existing work for natural question generation ignores the input passage or hard-codes answer positions. |
| Approach: | They propose a model that matches the answer with the passage before generating a question. |
| Outcome: | The proposed model outperforms the state-of-the-art model using rich features. |
Generalized Shortest-Paths Encoders for AMR-to-Text Generation (2020.coling-main)
Copied to clipboard
| Challenge: | a recent effort to encode graphs with gated convolutions provides local context, but distance messages travel is limited by number of encoder propagation steps. |
| Approach: | They propose to use generalized shortest-paths to train a graph encoder to learn shortest paths . they show that path diversity affects performance across levels of AMR connectivity . |
| Outcome: | The proposed model achieves a 1.4 BLEU and 1.8 chrF++ margin over a baseline model that encodes only pairwise-unique shortest paths. |
N-ary Relation Extraction using Graph-State LSTM (D18-1)
Copied to clipboard
| Challenge: | Existing methods for cross-sentence relation extraction split the input graph into two DAGs, but important information can be lost in the splitting procedure. |
| Approach: | They propose a graph-state LSTM model which uses a parallel state to model each word, recurrently enriching state values via message passing. |
| Outcome: | The proposed model keeps the original graph structure, and speeds up computation by allowing more parallelization. |