Papers › Linguistically-Informed Self-Attention for Semantic Role Labeling

Linguistically-Informed Self-Attention for Semantic Role Labeling

23 Apr 2018EMNLP 2018 10arXiv:1804.08199archive 2025-07-28

Emma Strubell, Patrick Verga, Daniel Andor, David Weiss, Andrew McCallum

Current state-of-the-art semantic role labeling (SRL) uses a deep neural network with no explicit linguistic features. However, prior work has shown that gold syntax trees can dramatically improve SRL decoding, suggesting the possibility of increased accuracy from explicit modeling of syntax. In this work, we present linguistically-informed self-attention (LISA): a neural network model that combines multi-head self-attention with multi-task learning across dependency parsing, part-of-speech tagging, predicate detection and SRL. Unlike previous models which require significant pre-processing to prepare linguistic features, LISA can incorporate syntax using merely raw tokens as input, encoding the sequence only once to simultaneously perform parsing, predicate detection and role labeling for all predicates. Syntax is incorporated by training one attention head to attend to syntactic parents for each token. Moreover, if a high-quality syntactic parse is already available, it can be beneficially injected at test time without re-training our SRL model. In experiments on CoNLL-2005 SRL, LISA achieves new state-of-the-art performance for a model using predicted predicates and standard word embeddings, attaining 2.5 F1 absolute higher than the previous state-of-the-art on newswire and more than 3.5 F1 on out-of-domain data, nearly 10% reduction in error. On ConLL-2012 English SRL we also show an improvement of more than 2.5 F1. LISA also out-performs the state-of-the-art with contextually-encoded (ELMo) word representations, by nearly 1.0 F1 on news and more than 2.0 F1 on out-of-domain text.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 14 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 14 samples from 1 repository, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

strubell/LISA officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: 14 samples, 9 ran (0 instrument-failed) · 5 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

9ran
5unverified

Licence: 0 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from strubell/LISA. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

strubell/LISA official repository 14 samples, 9 ran (0 instrument-failed) · 5 unverified
accuracy_np src/evaluation_fns_np.py ran Apache-2.0 (permissive) · e17ea0fc4873cd3e · report fixture: signature predictions:ndarray/1/int, targets:ndarray/1/int, mask:ndarray/1/int, accumulator:dict/0/? · returned float64 · level recorded 2026-09-25
convert_conll src/evaluation_fns_np.py ran Apache-2.0 (permissive) · 03c2cf6d3b1daf1b · report fixture: signature predicted_roles:list/1/str · returned map · level recorded 2026-09-25
get_default src/constants.py ran Apache-2.0 (permissive) · c2f375306505868b · report fixture: signature name:str/0/str · returned float · level recorded 2026-09-25
get_params in 53 papers src/attention_fns.py ran Apache-2.0 (permissive) · 0e84978dc1139b65 · report fixture: signature mode:str/0/str, attn_map:dict/0/?, train_outputs:dict/0/?, features:dict/0/?, labels:dict/0/? · returned dict · level recorded 2026-09-25
int_to_str_lookup_table src/nn_utils.py ran Apache-2.0 (permissive) · caca64fca95608c5 · report fixture: signature inputs:EagerTensor/1/int, lookup_map:dict/0/? · returned SymbolicTensor · level recorded 2026-09-25
lowercase_converter src/data_converters.py ran Apache-2.0 (permissive) · 413d686580cb441b · report fixture: signature split_line:list/1/str, idx:int/0/int · returned list · level recorded 2026-09-25
map_strings_to_ints src/dataset.py ran Apache-2.0 (permissive) · c7484be80663fcc6 · report fixture: signature vocab_lookup_ops:dict/0/?, data_config:dict/0/?, feature_label_names:list/1/str · returned function · level recorded 2026-09-25
parse_roots_self_loop_converter src/data_converters.py ran Apache-2.0 (permissive) · deaa9d2fd33c5349 · report fixture: signature split_line:list/1/str, idx:list/1/int · returned list · level recorded 2026-09-25
strip_conll12_domain_converter src/data_converters.py ran Apache-2.0 (permissive) · 15dbbde62d34c21c · report fixture: signature split_line:list/1/str, idx:int/0/int · returned list · level recorded 2026-09-25
accuracy_tf src/evaluation_fns.py unverified Apache-2.0 (permissive) · a8b322b3e51e24de · report
convert_bilou src/evaluation_fns_np.py unverified Apache-2.0 (permissive) · 9d94a9256be463e0 · report
create_metric_variable src/evaluation_fns.py unverified Apache-2.0 (permissive) · d5c0e80895ba13a2 · report
leaky_relu in 24 papers src/nn_utils.py unverified Apache-2.0 (permissive) · ea3b43b22b209a25 · report
set_vars_to_moving_average src/nn_utils.py unverified Apache-2.0 (permissive) · bbf19f387d296223 · report

Tasks

Dependency ParsingMulti-Task LearningPart-Of-Speech TaggingPredicate DetectionSemantic Role LabelingSemantic Role Labeling (predicted predicates)Word Embeddings

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Predicate Detection CoNLL 2005 LISA F1 98.4 #1 of 2 Archive leaderboard report
Predicate Detection CoNLL 2012 LISA F1 97.2 #1 of 1 Archive leaderboard report
Semantic Role Labeling CoNLL 2005 LISA F1 86.04 #12 of 15 Archive leaderboard report
Semantic Role Labeling (predicted predicates) CoNLL 2005 LISA + ELMo F1 86.90 #1 of 5 Archive leaderboard report
Semantic Role Labeling (predicted predicates) CoNLL 2005 LISA F1 84.99 #4 of 5 Archive leaderboard report
Semantic Role Labeling (predicted predicates) CoNLL 2012 LISA + ELMo F1 83.38 #3 of 7 Archive leaderboard report
Semantic Role Labeling (predicted predicates) CoNLL 2012 LISA F1 82.33 #6 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections