For over thirty years, researchers have developed and analyzed methods for latent tree induction as an approach for unsupervised syntactic parsing. Nonetheless, modern systems still do not perform well enough compared to their supervised counterparts
to have any practical use as structural annotation of text. In this work, we present a technique that uses distant supervision in the form of span constraints (i.e. phrase bracketing) to improve performance in unsupervised constituency parsing. Using a relatively small number of span constraints we can substantially improve the output from DIORA, an already competitive unsupervised parsing system. Compared with full parse tree annotation, span constraints can be acquired with minimal effort, such as with a lexicon derived from Wikipedia, to find exact text matches. Our experiments show span constraints based on entities improves constituency parsing on English WSJ Penn Treebank by more than 5 F1. Furthermore, our method extends to any domain where span constraints are easily attainable, and as a case study we demonstrate its effectiveness by parsing biomedical text from the CRAFT dataset.
We present our contribution to the IWPT 2021 shared task on parsing into enhanced Universal Dependencies. Our main system component is a hybrid tree-graph parser that integrates (a) predictions of spanning trees for the enhanced graphs with (b) addit
ional graph edges not present in the spanning trees. We also adopt a finetuning strategy where we first train a language-generic parser on the concatenation of data from all available languages, and then, in a second step, finetune on each individual language separately. Additionally, we develop our own complete set of pre-processing modules relevant to the shared task, including tokenization, sentence segmentation, and multiword token expansion, based on pre-trained XLM-R models and our own pre-training of character-level language models. Our submission reaches a macro-average ELAS of 89.24 on the test set. It ranks top among all teams, with a margin of more than 2 absolute ELAS over the next best-performing submission, and best score on 16 out of 17 languages.
In this paper, we present our systems submitted to SemEval-2021 Task 1 on lexical complexity prediction.The aim of this shared task was to create systems able to predict the lexical complexity of word tokens and bigram multiword expressions within a
given sentence context, a continuous value indicating the difficulty in understanding a respective utterance. Our approach relies on gradient boosted regression tree ensembles fitted using a heterogeneous feature set combining linguistic features, static and contextualized word embeddings, psycholinguistic norm lexica, WordNet, word- and character bigram frequencies and inclusion in wordlists to create a model able to assign a word or multiword expression a context-dependent complexity score. We can show that especially contextualised string embeddings can help with predicting lexical complexity.
We offer an approach to explain Decision Tree (DT) predictions by addressing potential conflicts between aspects of these predictions and plausible expectations licensed by background information. We define four types of conflicts, operationalize the
ir identification, and specify explanatory schemas that address them. Our human evaluation focused on the effect of explanations on users' understanding of a DT's reasoning and their willingness to act on its predictions. The results show that (1) explanations that address potential conflicts are considered at least as good as baseline explanations that just follow a DT path; and (2) the conflict-based explanations are deemed especially valuable when users' expectations disagree with the DT's predictions.
Abstract Although current CCG supertaggers achieve high accuracy on the standard WSJ test set, few systems make use of the categories' internal structure that will drive the syntactic derivation during parsing. The tagset is traditionally truncated,
discarding the many rare and complex category types in the long tail. However, supertags are themselves trees. Rather than give up on rare tags, we investigate constructive models that account for their internal structure, including novel methods for tree-structured prediction. Our best tagger is capable of recovering a sizeable fraction of the long-tail supertags and even generates CCG categories that have never been seen in training, while approximating the prior state of the art in overall tag accuracy with fewer parameters. We further investigate how well different approaches generalize to out-of-domain evaluation sets.
Abstract We give a general framework for inference in spanning tree models. We propose unified algorithms for the important cases of first-order expectations and second-order expectations in edge-factored, non-projective spanning-tree models. Our alg
orithms exploit a fundamental connection between gradients and expectations, which allows us to derive efficient algorithms. These algorithms are easy to implement with or without automatic differentiation software. We motivate the development of our framework with several cautionary tales of previous research, which has developed numerous inefficient algorithms for computing expectations and their gradients. We demonstrate how our framework efficiently computes several quantities with known algorithms, including the expected attachment score, entropy, and generalized expectation criteria. As a bonus, we give algorithms for quantities that are missing in the literature, including the KL divergence. In all cases, our approach matches the efficiency of existing algorithms and, in several cases, reduces the runtime complexity by a factor of the sentence length. We validate the implementation of our framework through runtime experiments. We find our algorithms are up to 15 and 9 times faster than previous algorithms for computing the Shannon entropy and the gradient of the generalized expectation objective, respectively.
Many wireless sensor network applications like forest fire detection and environment monitoring recommend making benefit from moving humans, vehicles, or animals to enhance network performance. In this research, we had improved our previous protocol
(Dynamic Tree Routing DTR) to support mobility in a wireless sensor network. First, we had mathematically approximated the speed threshold for mobile sensors, which enables them to successfully associate with nearby coordinators. Second, we test our (MDTR) protocol in a network with mobile sensors sending packets toward the network's main coordinator. The simulation results obtained from network Simulator (NS2) showed a good approximation of speed threshold, and good performance of MDTR in term of delay, throughput, and hop-count compared with AODV and MZBR Protocols.
Many wireless sensor network applications like forest fire detection and environment
monitoring recommend making benefit from moving humans, vehicles, or animals to
enhance network performance. In this research, we had improved our previous protoco
l
(Dynamic Tree Routing DTR) in order to support mobility in a wireless sensor network.
First, we had mathematically approximated the speed threshold for mobile sensors, which
enables them to successfully associate with nearby coordinators. Second, we test our
(MDTR) protocol in a network with mobile sensors sending packets toward network's
main coordinator. The simulation results obtained from network Simulator (NS2) showed a
good approximation of speed threshold, and good performance of MDTR in term of delay,
throughput, and hop-count compared with AODV and MZBR Protocols.
Brutia pine tree grows radially and gives one ring per year, the width of
this ring is determined by environmental conditions especially by climatic
ones. Dendroclimatology concerns with studying the response of tree rings
to climatic conditions.
In order to study the radial growth of brutia pine
planted 1975 in Heir Brafa, Tartous, Syria.
The study was achieved in 2014-2015 at Dahr Khribat stone pine forest, Latakia. to
determine the factors affecting the natural regeneration of the stand. The results of climate
studies indicated that the region is located in the semi-wet climate fl
oor with a mild winter
as the average of rainfall thermal coefficient reached (Q2 = 72.01). The study showed that
the low productivity of cones (20 kg con / tree) was one of the limiting factors of natural
regeneration. The trees high density (462 tree / ha), led to a decrease in tree diameter at
breast level (30 cm) and low coronary size (320.2 m3).
Seed germination was not affected by illumination periods, while salinity levels led
to a significant decrease in germination from 90% at control to 19% at 0.5 mol / l.
All of one year old sapling or seedling were dead during summer months, while more
than 90% of two years old cultivated sapling, survived in all treatments, but no significant
differences among them.
